© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15017
    Prev
    Next
    INDEX
    Explanations

    code definitions

    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
    UAWEI
    -1.68
     komik
    -1.68
     cuidadosamente
    -1.68
    ﹶ
    -1.66
     rápidamente
    -1.55
    Rumah
    -1.55
    Waktu
    -1.54
    bouw
    -1.53
    嫱
    -1.51
     secador
    -1.50
    POSITIVE LOGITS
     of
    2.36
    4
    1.74
     $=\
    1.67
    y
    1.59
     have
    1.58
    到
    1.55
    )$.
    1.55
    os
    1.54
    就像是
    1.50
    in
    1.48
    Activations Density 0.007%

    No Known Activations