© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36441
    Prev
    Next
    INDEX
    Explanations

    numbers followed by digits

    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
    bigr
    -1.18
    dengan
    -1.17
     шанс
    -1.15
    멧
    -1.13
     מן
    -1.13
    🤑
    -1.13
     незавер
    -1.12
     réflé
    -1.12
    Trichloroethane
    -1.12
    НР
    -1.11
    POSITIVE LOGITS
     allemaal
    1.33
    紧接着
    1.29
    接著
    1.11
     blauen
    1.08
     Dusche
    1.05
     also
    1.03
     our
    1.00
     zusätz
    1.00
     gesamten
    0.99
    
    0.99
    Activations Density 0.020%

    No Known Activations