© 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. 128462
    Prev
    Next
    INDEX
    Explanations

    Appeal from court filings

    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
    \
    -2.33
    ations
    -2.09
     This
    -2.06
    M
    -1.95
     \
    -1.78
    L
    -1.74
    or
    -1.72
    鐃
    -1.70
     /
    -1.70
     \\
    -1.69
    POSITIVE LOGITS
     we
    2.75
     underscores
    1.77
    serves
    1.74
     salvaje
    1.73
    時の
    1.72
    焄
    1.72
    increases
    1.71
    ſelf
    1.71
    klü
    1.71
    ,’
    1.67
    Activations Density 0.021%

    No Known Activations