© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13565
    Prev
    Next
    INDEX
    Explanations

    names and questions

    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
    ↵
    -2.05
    </strong>
    -1.99
     $
    -1.93
    -
    -1.83
    ".
    -1.73
    \_
    -1.73
     siete
    -1.68
    ,*
    -1.63
     \_
    -1.59
     exposes
    -1.59
    POSITIVE LOGITS
    呖
    1.76
     Holiness
    1.71
     函数
    1.69
     искрен
    1.68
    ﹍﹍
    1.61
     '';
    1.59
     車場
    1.55
    ꯶
    1.55
    ſelves
    1.55
     模型
    1.53
    Activations Density 0.003%

    No Known Activations