© 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. 22-GEMMASCOPE-RES-131K
    7. 12923
    Prev
    Next
    INDEX
    Explanations

    legal document terms

    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
    mathrm
    -1.15
     фильтр
    -1.12
     Automó
    -1.06
    没有
    -1.02
     CGRectMake
    -1.00
     Libraries
    -0.99
    Erstellt
    -0.98
    menden
    -0.98
    Jeśli
    -0.96
    即購入
    -0.96
    POSITIVE LOGITS
    爆笑
    1.02
    küche
    1.02
    干部
    1.02
     meninos
    0.99
    Reti
    0.97
    Spelling
    0.96
    colnshire
    0.95
     заметил
    0.95
    这样一个
    0.93
    Impressive
    0.92
    Activations Density 0.015%

    No Known Activations