© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44142
    Prev
    Next
    INDEX
    Explanations

    1 followed by operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    臜
    -1.71
    ENTON
    -1.66
    毳
    -1.63
     包装
    -1.58
     迷你
    -1.57
    鹪
    -1.56
     アイコン
    -1.53
    蹰
    -1.53
    虓
    -1.50
     brak
    -1.49
    POSITIVE LOGITS
     by
    2.06
     through
    1.96
     from
    1.95
     or
    1.89
     with
    1.81
     in
    1.78
     on
    1.77
     one
    1.59
     it
    1.54
     legyen
    1.47
    Activations Density 0.016%

    No Known Activations