© 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. 34-GEMMASCOPE-RES-131K
    7. 30892
    Prev
    Next
    INDEX
    Explanations

    instructions and requests

    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
     extrême
    -0.95
     rác
    -0.93
     silêncio
    -0.92
     majeur
    -0.91
     bò
    -0.91
    很想
    -0.90
     Thần
    -0.90
     dán
    -0.89
     Quận
    -0.88
     Quý
    -0.87
    POSITIVE LOGITS
     each
    0.93
     should
    0.85
     knew
    0.79
     then
    0.76
     зовні
    0.75
     solidaridad
    0.75
     pedag
    0.74
    operatives
    0.73
     blatantly
    0.73
    每個
    0.73
    Activations Density 0.001%

    No Known Activations