© 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. 8066
    Prev
    Next
    INDEX
    Explanations

    quoted text or names

    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
    蘩
    -2.44
    𓍊
    -2.31
    虓
    -2.11
     alemão
    -2.06
    楽しかった
    -2.05
     Lingkungan
    -1.95
     politique
    -1.93
    鴟
    -1.91
     Bedürfn
    -1.90
    浔
    -1.90
    POSITIVE LOGITS
    as
    2.50
    m
    2.42
    '
    2.34
    ti
    2.28
     Then
    2.25
    )){
    2.16
    S
    2.08
    X
    2.08
    J
    2.08
    to
    2.03
    Activations Density 0.033%

    No Known Activations