© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1046
    Prev
    Next
    INDEX
    Explanations

    information related to substance abuse and its consequences.

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

    articles and prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     бонусу
    0.26
     paralysie
    0.24
     девушки
    0.24
     setzt
    0.23
     esimerk
    0.23
     überprü
    0.23
     obfusc
    0.23
    ཋ
    0.23
     chante
    0.22
    ⵎ
    0.22
    POSITIVE LOGITS
     the
    0.45
     a
    0.30
     an
    0.30
     your
    0.30
     suatu
    0.28
    0.27
     certain
    0.26
    the
    0.26
     his
    0.26
    ↵
    0.23
    Activations Density 3.324%

    No Known Activations