© 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. 71232
    Prev
    Next
    INDEX
    Explanations

    starts of titles or names

    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
    翆
    -1.87
    es
    -1.80
    擽
    -1.72
    了一個
    -1.70
    n
    -1.68
    縢
    -1.68
     薬局
    -1.67
    o
    -1.66
    ﹍﹍
    -1.64
    顚
    -1.63
    POSITIVE LOGITS
     or
    2.11
     we
    2.11
    </strong>
    2.03
    .
    1.86
    ığımız
    1.82
     and
    1.78
     هذه
    1.77
     این
    1.72
     nossa
    1.68
     worin
    1.67
    Activations Density 0.000%

    No Known Activations