© 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. 38834
    Prev
    Next
    INDEX
    Explanations

    languages, dataframe, csv, image

    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
    ög
    0.86
    辕
    0.81
    ’
    0.80
    ers
    0.77
     realizados
    0.75
    ются
    0.74
    å
    0.74
    ors
    0.71
    ан
    0.71
    പ്പോ
    0.70
    POSITIVE LOGITS
    愍
    0.83
    مع
    0.80
     fearing
    0.79
     njemu
    0.79
    بية
    0.77
     igra
    0.76
    galkan
    0.75
     feared
    0.74
    ⿺
    0.74
    لي
    0.73
    Activations Density 0.000%

    No Known Activations