© 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. 7488
    Prev
    Next
    INDEX
    Explanations

    viewed as

    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
    姈
    -2.28
    ="
    -2.06
    section
    -1.83
    ни
    -1.82
    われている
    -1.80
    丝毫
    -1.77
    碾
    -1.77
    的所有
    -1.70
     Thus
    -1.68
    ganie
    -1.68
    POSITIVE LOGITS
    '
    2.38
    小时候
    2.23
    It
    2.16
    If
    2.06
    You
    2.00
    There
    1.95
     that
    1.89
     viewed
    1.89
    ки
    1.82
    *
    1.82
    Activations Density 0.004%

    No Known Activations