© 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. 22219
    Prev
    Next
    INDEX
    Explanations

    markup and code structures

    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
     to
    -2.03
    INTRODUCCIÓN
    -1.73
     lietu
    -1.70
     viena
    -1.70
     darbo
    -1.69
     vanden
    -1.68
     vieta
    -1.63
    perative
    -1.60
     moks
    -1.55
    ︲
    -1.55
    POSITIVE LOGITS
    .
    2.86
    <i>
    1.84
    ).
    1.78
    :
    1.76
    ↵↵
    1.75
    人气
    1.74
    )
    1.60
     required
    1.53
    <b>
    1.52
    而成
    1.51
    Activations Density 0.068%

    No Known Activations