© 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. 38145
    Prev
    Next
    INDEX
    Explanations

    won't / wins

    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
    ก
    2.30
    ture
    2.28
    ی
    2.27
    ك
    2.22
    aquest
    2.19
    cómo
    2.09
    存于互联网档案馆
    2.08
    tanggal
    2.08
    tio
    2.08
    pictured
    2.06
    POSITIVE LOGITS
    ok
    2.13
    ir
    2.03
    ু
    1.99
    शिप
    1.97
    ا
    1.95
    ز
    1.81
     Values
    1.73
    ून
    1.72
    ी
    1.72
    al
    1.70
    Activations Density 0.019%

    No Known Activations