© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127416
    Prev
    Next
    INDEX
    Explanations

    configuration files define

    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
    u
    -3.91
    that
    -3.58
    *
    -3.34
    on
    -3.14
    3
    -2.98
    an
    -2.92
    as
    -2.88
    を
    -2.88
    1
    -2.70
    -2.61
    POSITIVE LOGITS
    ࿊
    3.56
    锖
    2.88
    嵙
    2.86
     bénévol
    2.77
    噲
    2.72
    接下来的
    2.67
    せない
    2.66
    ﹍﹍
    2.59
     môžu
    2.58
     partenaire
    2.56
    Activations Density 0.001%

    No Known Activations