© 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. 14435
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
    橚
    -2.19
     própri
    -1.89
    粜
    -1.88
    
    -1.87
     deliciously
    -1.79
    嘴里
    -1.78
     exhilarating
    -1.77
     convaincre
    -1.75
     delightfully
    -1.73
     VERY
    -1.71
    POSITIVE LOGITS
     This
    1.86
     There
    1.80
     in
    1.79
     Even
    1.77
     it
    1.74
     or
    1.68
     Despite
    1.67
     have
    1.66
    Despite
    1.63
    嗚
    1.63
    Activations Density 0.003%

    No Known Activations