© 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. 64437
    Prev
    Next
    INDEX
    Explanations

    document section titles

    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
    や
    -0.91
    <bos>
    -0.89
     consequent
    -0.87
    henswürdigkeiten
    -0.86
    ensões
    -0.86
    その
    -0.85
     Kategorien
    -0.84
     sendo
    -0.84
     как
    -0.84
     being
    -0.84
    POSITIVE LOGITS
    為に
    1.02
    Twice
    1.00
    toim
    0.98
    ところに
    0.97
     twice
    0.93
    Antibodies
    0.92
    骄傲
    0.91
    を行います
    0.88
     hubieran
    0.88
     congratulated
    0.86
    Activations Density 0.006%

    No Known Activations