© 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. 977
    Prev
    Next
    INDEX
    Explanations

    family

    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
    را
    1.85
    ق
    1.83
    ܢܐ
    1.73
    ிகா
    1.63
    昻
    1.60
     ambientale
    1.46
    ทางการ
    1.45
     mortem
    1.45
    ्रे
    1.43
     développ
    1.40
    POSITIVE LOGITS
    er
    1.92
    d
    1.89
    。
    1.85
    amp
    1.84
    ।
    1.74
    。\
    1.73
    icidal
    1.61
    ati
    1.55
     Вы
    1.44
    erver
    1.42
    Activations Density 0.019%

    No Known Activations