© 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. 14823
    Prev
    Next
    INDEX
    Explanations

    2

    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
     برابر
    0.60
     cellpadding
    0.56
    Especially
    0.55
    衫
    0.55
    Keeping
    0.54
    ض
    0.54
    germ
    0.54
     एकमे
    0.53
    PTH
    0.52
    ongan
    0.51
    POSITIVE LOGITS
     attain
    0.57
     merr
    0.57
     Ramirez
    0.56
    oir
    0.55
     요거
    0.55
    ሺ
    0.54
     ২০১৬
    0.53
     предвари
    0.52
     น่า
    0.52
     opener
    0.52
    Activations Density 0.075%

    No Known Activations