© 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. 66268
    Prev
    Next
    INDEX
    Explanations

    chairman, operator, judge, counsel

    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
     cuyos
    -1.11
     somente
    -1.05
     predominantly
    -1.05
     pertenec
    -1.04
     vão
    -1.02
     extremely
    -1.02
     foarte
    -1.01
     cuyas
    -1.01
     decenas
    -1.00
     supuestamente
    -1.00
    POSITIVE LOGITS
    🌼
    1.23
     diras
    1.20
    😸
    1.19
    ❄️
    1.11
     politika
    1.08
    ☀️
    1.06
    🌻
    1.05
     eser
    1.04
     febr
    1.02
    😻
    1.02
    Activations Density 0.065%

    No Known Activations