© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2898
    Prev
    Next
    INDEX
    Explanations

    model answers

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

    the token that marks the model/assistant’s turn in a chat transcript.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
     ESM
    0.33
     пользователя
    0.33
    ्योर
    0.31
     रव
    0.31
     большой
    0.31
     úrov
    0.31
     большим
    0.30
    ﾛ
    0.30
    Cuánto
    0.30
    伡
    0.30
    POSITIVE LOGITS
    answer
    0.35
    Sources
    0.33
    Wikipedia
    0.33
     Sources
    0.31
     answer
    0.31
    sources
    0.31
    Answer
    0.30
    Mutual
    0.30
     Guinness
    0.29
    Sadly
    0.29
    Activations Density 0.006%

    No Known Activations