© 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-16K
    7. 1106
    Prev
    Next
    INDEX
    Explanations

    multi-lingual characters

    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_16k_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
    ри
    2.44
    ти
    1.98
    ро
    1.88
    篌
    1.72
    ний
    1.69
    が終わ
    1.66
    ைட்
    1.65
     플러스
    1.64
     вкус
    1.62
     FODC
    1.61
    POSITIVE LOGITS
    א
    2.83
    ح
    2.22
    ve
    1.96
    ことを
    1.90
    有了
    1.88
    து
    1.86
    ath
    1.82
    ll
    1.74
    아
    1.73
    od
    1.73
    Activations Density 1.507%

    No Known Activations