© 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. 73425
    Prev
    Next
    INDEX
    Explanations

    prop or props

    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
    le
    -2.30
    3
    -2.16
    ve
    -2.09
    is
    -1.98
    2
    -1.96
    『
    -1.82
    d
    -1.80
    of
    -1.78
    (
    -1.68
    =
    -1.63
    POSITIVE LOGITS
     欣赏
    1.81
    汌
    1.77
    찡
    1.76
    راقي
    1.75
    を始め
    1.73
     holen
    1.73
    𓁹
    1.72
    ٶ
    1.72
    .$,
    1.68
    argp
    1.68
    Activations Density 0.014%

    No Known Activations