© 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. 87081
    Prev
    Next
    INDEX
    Explanations

    division and programming concepts

    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
    Compiled
    -0.75
     prohibitive
    -0.73
     Radiology
    -0.73
     Ленинград
    -0.73
    MES
    -0.72
     Personen
    -0.71
     incur
    -0.71
    شود
    -0.71
     diberikan
    -0.71
     然
    -0.70
    POSITIVE LOGITS
     divi
    0.97
     Divis
    0.92
     Divi
    0.90
     تقسیم
    0.88
     voti
    0.85
     APM
    0.84
     pagamento
    0.81
    0.81
    thalt
    0.81
     Div
    0.80
    Activations Density 0.037%

    No Known Activations