© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 0
    Prev
    Next
    INDEX
    Explanations

    key concepts and definitions related to signals intelligence and its subcategories.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    indicates that

    np_acts-logits-general · gemini-2.5-flash-lite

    The marked tokens across examples consistently appear at points where a verb or phrase conveys critical information—particularly verbs indicating discovery, statement, or logical connection (such as "indicates," "suggests," "shows," "found," "highlights," "demonstrates," "concludes"). These tokens mark linguistically important nodes where key claims, findings, or logical progressions occur in informational or explanatory text.

    eleuther_acts_top20 · claude-4-5-haikuTriggered by @jamesnaruto04
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     +
    0.23
     eller
    0.22
     +,
    0.21
     เหมาะ
    0.20
    }.
    0.20
     każdego
    0.20
     kalian
    0.20
     সুতরাং
    0.20
     тебя
    0.19
     دە
    0.19
    POSITIVE LOGITS
     bahwa
    0.47
     faptul
    0.45
     bahawa
    0.45
     rằng
    0.43
     ότι
    0.39
    that
    0.38
     أنه
    0.37
     that
    0.34
    ว่า
    0.34
     أنّ
    0.32
    Activations Density 0.883%

    No Known Activations