© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7947
    Prev
    Next
    INDEX
    Explanations

    quiz, quizzes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ى
    1.80
    นอน
    1.66
    zelfde
    1.64
    enyl
    1.64
    兕
    1.54
    tır
    1.53
    лили
    1.52
    İ
    1.52
    рів
    1.51
    ない
    1.50
    POSITIVE LOGITS
    c
    2.03
    ется
    1.75
    ic
    1.74
    v
    1.70
    ことは
    1.69
    ătoare
    1.69
    вная
    1.63
    ా
    1.63
    ваме
    1.61
     vivos
    1.59
    Activations Density 0.025%

    No Known Activations