© 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. 8598
    Prev
    Next
    INDEX
    Explanations

    LEGO bricks

    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
    부터
    1.86
     alcuna
    1.69
    ت
    1.63
    특별시
    1.60
    मध्ये
    1.54
    いた
    1.52
    ्ता
    1.48
    నం
    1.46
    pflicht
    1.46
    aft
    1.45
    POSITIVE LOGITS
    ak
    2.17
    و
    1.76
    P
    1.71
    K
    1.66
    f
    1.63
    am
    1.59
    os
    1.56
    is
    1.52
    n
    1.48
    ิ
    1.48
    Activations Density 0.000%

    No Known Activations