© 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. 34-GEMMASCOPE-RES-131K
    7. 116078
    Prev
    Next
    INDEX
    Explanations

    code structures with values

    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_34/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
     another
    -1.12
    雀
    -0.97
     still
    -0.97
    Another
    -0.95
     Those
    -0.93
     bataille
    -0.93
     those
    -0.92
    武者
    -0.91
     with
    -0.88
     hundreds
    -0.88
    POSITIVE LOGITS
     einander
    0.98
     SIMILAR
    0.91
    愜
    0.90
     stärker
    0.89
     similaire
    0.88
    ブラウン
    0.85
    リンク
    0.84
    靦
    0.84
     dominante
    0.84
    の基本
    0.84
    Activations Density 0.112%

    No Known Activations