© 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. 6166
    Prev
    Next
    INDEX
    Explanations

    great wall

    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
    ak
    1.90
    ments
    1.61
    nails
    1.38
    ная
    1.38
     glutamate
    1.38
    am
    1.32
    на
    1.32
    א
    1.30
    我
    1.30
    ন
    1.29
    POSITIVE LOGITS
    Fuente
    1.31
     eslint
    1.30
    ‌است
    1.27
    TTY
    1.24
     মির
    1.23
     opcion
    1.21
    ۰۰
    1.19
    ვ
    1.19
    ﺙ
    1.18
    TODO
    1.16
    Activations Density 0.000%

    No Known Activations