© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14798
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     adjust
    0.59
     adjusts
    0.59
    Adjust
    0.59
    调整
    0.57
    =|
    0.57
    鬟
    0.57
    ස්ට
    0.55
    当
    0.54
    迷
    0.54
    鮫
    0.54
    POSITIVE LOGITS
     Body
    0.57
    ကား
    0.57
    タリア
    0.55
     Chili
    0.52
     HIR
    0.52
     Highway
    0.51
    eea
    0.51
    नाचा
    0.51
    ССР
    0.50
     شعر
    0.50
    Activations Density 0.000%

    No Known Activations