© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76922
    Prev
    Next
    INDEX
    Explanations

    copyright year author

    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
     zač
    -0.88
    Reklama
    -0.87
    feste
    -0.86
    SEGUIR
    -0.85
    ";
    -0.84
     neces
    -0.81
    ってください
    -0.80
    〞
    -0.79
     með
    -0.78
    ってみる
    -0.77
    POSITIVE LOGITS
    <h5>
    1.47
    <h6>
    0.93
     inverse
    0.75
     decode
    0.75
     sting
    0.74
     strange
    0.73
     intentional
    0.73
    颂
    0.72
     illegal
    0.72
     производится
    0.71
    Activations Density 0.006%

    No Known Activations