© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62454
    Prev
    Next
    INDEX
    Explanations

    function declarations

    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
    Negative Logits
     réussite
    -0.91
    ((
    -0.88
    去找
    -0.79
    żs
    -0.78
     أبو
    -0.78
    つまり
    -0.76
     zrobić
    -0.76
     ajuta
    -0.75
    淌
    -0.75
     显
    -0.74
    POSITIVE LOGITS
    void
    1.77
     void
    1.63
    const
    1.06
     const
    1.02
    register
    0.98
     voids
    0.91
     registra
    0.90
    <0xF1>
    0.87
    MongoClient
    0.86
     struct
    0.85
    Activations Density 0.012%

    No Known Activations