© 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. 34-GEMMASCOPE-RES-131K
    7. 103472
    Prev
    Next
    INDEX
    Explanations

    Eclipse LLVM preferences

    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_34/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
     Wikispecies
    -0.73
    Fuji
    -0.72
     inga
    -0.72
     tertutup
    -0.72
    Scaffold
    -0.71
     CLUB
    -0.71
    عاون
    -0.71
     szól
    -0.70
    chino
    -0.68
    Cobra
    -0.68
    POSITIVE LOGITS
     simbolo
    0.81
    pañas
    0.79
    chlag
    0.76
    น้อง
    0.76
    跳转
    0.75
    afficher
    0.74
     Phar
    0.73
     夕
    0.73
    tidaknya
    0.73
     メーカー
    0.72
    Activations Density 0.003%

    No Known Activations