© 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. 71863
    Prev
    Next
    INDEX
    Explanations

    code and math formatting

    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
    Ӈ
    -1.00
    못
    -0.98
    neiden
    -0.98
    Кроме
    -0.98
    そんな
    -0.95
    ikti
    -0.95
    薔薇
    -0.95
     }{@
    -0.94
    ücher
    -0.94
    шить
    -0.94
    POSITIVE LOGITS
     Schülern
    1.16
    licante
    1.11
    rugu
    1.05
    vaila
    1.04
    lden
    1.04
     aktualisiert
    1.02
    izzazioni
    1.00
    着自己的
    1.00
    verwaltung
    0.99
     ejemplares
    0.99
    Activations Density 0.069%

    No Known Activations