© 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. 144658
    Prev
    Next
    INDEX
    Explanations

    actions and activities

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

    legal, crimes, loss

    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
    タ
    0.62
    닐
    0.56
    サイズ
    0.54
    ૦
    0.52
    ア
    0.52
    IR
    0.50
    ある
    0.50
    ir
    0.50
    ба
    0.49
    īt
    0.49
    POSITIVE LOGITS
     unscrupulous
    0.47
     detrimental
    0.46
     outlandish
    0.46
    pojo
    0.45
     Sou
    0.44
     crimes
    0.43
     traumat
    0.43
     Pied
    0.42
     sou
    0.42
     prejudicial
    0.42
    Activations Density 0.000%

    No Known Activations