© 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. 59836
    Prev
    Next
    INDEX
    Explanations

    get away with or from

    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
    慙
    -2.52
    豨
    -2.25
    鹛
    -2.22
    餿
    -2.19
    鱻
    -2.16
    錞
    -2.13
    棐
    -2.13
    卨
    -2.11
    癭
    -2.09
    the
    -2.06
    POSITIVE LOGITS
    峙
    2.02
     Isn
    1.95
    “,
    1.76
     ใน
    1.76
     mehrere
    1.76
     In
    1.75
    ">“
    1.71
    腕
    1.70
    外科
    1.67
    plained
    1.66
    Activations Density 0.001%

    No Known Activations