© 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. 40-GEMMASCOPE-2-RES-262K
    4. 11539
    Prev
    Next
    INDEX
    Explanations

    phrases following punctuation or conjunctions

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

    things that look like numeric identifiers, product codes, measurements, or other document metadata/formatting tokens (numbers, codes, and technical labels).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    !),
    0.27
    ën
    0.26
     appunto
    0.25
     itibaren
    0.22
     ומ
    0.22
    Í
    0.22
    !).
    0.22
    Ë
    0.22
    efeu
    0.21
     આપણે
    0.21
    POSITIVE LOGITS
    𝑥
    0.24
     phd
    0.23
     Walmart
    0.22
     blah
    0.22
     regret
    0.22
     букмекерлар
    0.22
     bốn
    0.22
     Uzbekistan
    0.21
     q
    0.21
    定義
    0.21
    Activations Density 1.874%

    No Known Activations