© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11521
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

    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
    nehin
    -1.04
    Zubereitung
    -1.01
    我的
    -1.01
     culturelle
    -0.97
    оны
    -0.96
    我们的
    -0.96
    ‼️
    -0.95
     augusti
    -0.94
    ◗
    -0.93
     Pada
    -0.93
    POSITIVE LOGITS
    Nguy
    0.90
     admitir
    0.90
     flotante
    0.88
    Aplica
    0.87
    losseum
    0.85
     acolo
    0.84
    又有
    0.84
     útil
    0.83
     extensão
    0.83
     explicó
    0.82
    Activations Density 0.024%

    No Known Activations