© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14481
    Prev
    Next
    INDEX
    Explanations

    computing technical terms

    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
     ≥
    0.88
     ≤
    0.84
     wherein
    0.80
    ≥
    0.80
     thereby
    0.74
    ⩾
    0.73
    wherein
    0.71
    ≤
    0.70
     régler
    0.68
    依次
    0.64
    POSITIVE LOGITS
    狧
    0.62
    Hoje
    0.61
    発達
    0.60
    世紀
    0.59
    事実
    0.59
     කෙ
    0.59
     बदनाम
    0.59
     ഇത്തരം
    0.58
     raczej
    0.58
     совсем
    0.57
    Activations Density 0.000%

    No Known Activations