© 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. 43922
    Prev
    Next
    INDEX
    Explanations

    predominant followed by description

    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
     是
    -2.83
    ка
    -2.81
    e
    -2.59
    他不
    -2.48
    푘
    -2.47
    ra
    -2.39
    me
    -2.39
    сти
    -2.36
    ent
    -2.34
    ha
    -2.27
    POSITIVE LOGITS
    结语
    2.95
    翼翼
    2.69
    最后由
    2.63
    綃
    2.47
    vantaged
    2.41
    Пусть
    2.39
    其妙
    2.31
    比如说
    2.28
    縝
    2.27
     huevos
    2.23
    Activations Density 0.004%

    No Known Activations