© 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. 67612
    Prev
    Next
    INDEX
    Explanations

    strive to

    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
    ről
    -2.17
    嘖
    -2.05
    変わる
    -1.83
    今では
    -1.82
    彼女は
    -1.79
    蜴
    -1.75
     наличии
    -1.72
    𖤍
    -1.70
    始化
    -1.70
    我一直
    -1.69
    POSITIVE LOGITS
    它
    2.02
    ’
    1.99
    他
    1.88
     seperti
    1.87
    *
    1.84
    an
    1.80
     it
    1.79
    所有
    1.76
     WHILE
    1.76
    o
    1.59
    Activations Density 0.007%

    No Known Activations