© 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. 15091
    Prev
    Next
    INDEX
    Explanations

    average

    np_max-act-logits · gemini-2.5-flash-lite
    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
     도형
    0.59
     Partners
    0.57
     सेंटी
    0.56
     бухгалтер
    0.56
     Θ
    0.55
     Got
    0.54
     Ezekiel
    0.54
     Dollars
    0.53
    シンプル
    0.52
    Got
    0.52
    POSITIVE LOGITS
    reader
    0.64
     Cope
    0.58
     reader
    0.57
     tích
    0.55
    igraphy
    0.52
    spare
    0.52
    READER
    0.52
    Reader
    0.52
    𝙞
    0.52
     آئی
    0.51
    Activations Density 0.001%

    No Known Activations