© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 307
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ının
    0.86
    РА
    0.85
    َا
    0.85
    лары
    0.85
    ِي
    0.83
    ünün
    0.83
     affirmat
    0.83
    रेक्ट
    0.81
     abilit
    0.81
     inherent
    0.81
    POSITIVE LOGITS
     ペンダント
    0.77
     キッズ
    0.76
     जगदीश
    0.71
     latter
    0.70
     袖
    0.69
     コットン
    0.68
     Hall
    0.68
    0
    0.67
     South
    0.66
     秋冬
    0.65
    Activations Density 0.989%

    No Known Activations