© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180477
    Prev
    Next
    INDEX
    Explanations

    she playsmodern world

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

    due to, auto Snap, sibling, suffixes, large baked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    0.48
    </code>
    0.43
     Radiation
    0.42
     −
    0.42
     year
    0.41
    –
    0.41
     sequence
    0.41
     energy
    0.41
    ngày
    0.41
     result
    0.41
    POSITIVE LOGITS
    也很
    0.47
    thew
    0.46
    権利
    0.45
    失敗
    0.45
     saker
    0.44
    📹
    0.44
    露出
    0.44
    出现在
    0.43
     اعلان
    0.43
     Halke
    0.43
    Activations Density 0.000%

    No Known Activations