© 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. 22-GEMMASCOPE-RES-131K
    7. 38523
    Prev
    Next
    INDEX
    Explanations

    path separators and identifiers

    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_22/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
     aprecia
    -1.11
    annen
    -1.04
     lesquelles
    -1.04
    >';
    -1.04
     kardashian
    -1.02
     Uncategorized
    -1.02
     ウッド
    -1.01
     iyon
    -1.01
    のだろう
    -1.00
    ֎
    -1.00
    POSITIVE LOGITS
    étrie
    0.95
     by
    0.94
     фонд
    0.93
     my
    0.89
     इन
    0.86
    e
    0.85
    了啊
    0.85
    As
    0.85
    ση
    0.84
    a
    0.82
    Activations Density 0.424%

    No Known Activations