© 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. 10-GEMMASCOPE-RES-131K
    7. 75072
    Prev
    Next
    INDEX
    Explanations

    programming function definitions

    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_10/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
    '
    -2.06
    ：　
    -1.82
    部は
    -1.77
    鱟
    -1.71
     lavoratori
    -1.69
    arono
    -1.64
    ↵↵
    -1.63
    柃
    -1.59
    名は
    -1.59
     vacunación
    -1.58
    POSITIVE LOGITS
     Können
    1.88
    We
    1.77
    i
    1.76
     Of
    1.70
     It
    1.70
     Vielleicht
    1.63
     Sedangkan
    1.59
     Entfer
    1.56
     Namun
    1.55
     Verkä
    1.53
    Activations Density 0.001%

    No Known Activations