© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13179
    Prev
    Next
    INDEX
    Explanations

    hit or collision actions

    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
    itarias
    -1.11
    遽
    -1.09
    锢
    -1.09
     manifestación
    -1.00
     lendemain
    -0.98
    yorsunuz
    -0.97
     Productos
    -0.97
    معلومات
    -0.96
     Responsable
    -0.96
     Konkur
    -0.95
    POSITIVE LOGITS
     felt
    1.03
     گیری
    1.00
     areas
    0.98
    Inne
    0.98
     попада
    0.98
     raggi
    0.97
     interaction
    0.96
     atento
    0.96
     wanted
    0.93
    areas
    0.93
    Activations Density 0.003%

    No Known Activations