© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103108
    Prev
    Next
    INDEX
    Explanations

    misuse

    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
     are
    -2.47
     to
    -2.38
     encompassing
    -2.14
     sometime
    -2.14
    ৄ
    -2.11
    l
    -2.08
     possessing
    -2.02
     originally
    -1.95
    [
    -1.95
    n
    -1.95
    POSITIVE LOGITS
    on
    2.50
     صفحۀ
    2.22
    8
    2.11
    it
    2.06
     russes
    2.05
    рюкзак
    2.05
     impotent
    1.96
    6
    1.95
    或者
    1.89
    塤
    1.88
    Activations Density 0.002%

    No Known Activations