© 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. 14615
    Prev
    Next
    INDEX
    Explanations

    type, RUN, path

    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
    茈
    -2.02
    fromUtf
    -1.79
    蕻
    -1.77
    焢
    -1.72
     همچ
    -1.61
     leyenda
    -1.60
     ricas
    -1.59
    臯
    -1.58
    extAlignment
    -1.52
     sentimos
    -1.52
    POSITIVE LOGITS
     that
    2.20
    喲
    1.84
     most
    1.77
     It
    1.68
     this
    1.57
    føre
    1.52
    ↵↵
    1.51
     about
    1.49
     only
    1.46
    ？！
    1.45
    Activations Density 0.002%

    No Known Activations