© 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-262K
    7. 241488
    Prev
    Next
    INDEX
    Explanations

    initialization methods

    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_262k_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
     voltaje
    0.58
    талия
    0.54
    陴
    0.54
    onedDateTime
    0.54
     되는
    0.53
     삭제
    0.53
    변경된
    0.53
    님의
    0.52
     нижней
    0.52
    ੰ
    0.51
    POSITIVE LOGITS
     initWithFrame
    0.68
     With
    0.61
     Với
    0.61
    with
    0.59
    WithSize
    0.58
    With
    0.58
     [[[
    0.58
     aDecoder
    0.57
     Dengan
    0.56
     convenience
    0.56
    Activations Density 0.000%

    No Known Activations