Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31176
    Prev
    Next
    INDEX
    Explanations

    extension, hunting, orography

    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
    سي
    1.11
    са
    1.09
    ਸ਼
    1.06
    л
    1.04
    ட்
    1.03
    يين
    1.00
    ט
    0.99
     sól
    0.99
    يق
    0.95
    η
    0.95
    POSITIVE LOGITS
     Комп
    0.82
    Http
    0.82
    sprech
    0.81
    marquee
    0.80
    Item
    0.78
     Fools
    0.76
    графія
    0.76
    Helpers
    0.75
    mard
    0.74
     Ін
    0.73
    Activations Density 0.000%

    No Known Activations