© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    extract information

    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
    т
    2.67
    त
    2.42
    на
    2.38
    ோ
    2.34
    ت
    2.31
    ک
    2.31
    MAN
    2.25
    та
    2.22
    ра
    2.20
    ль
    2.20
    POSITIVE LOGITS
    son
    2.11
     Esses
    2.00
    mente
    1.93
    ssä
    1.90
    d
    1.88
    mers
    1.88
    nums
    1.84
    を有
    1.83
    ب
    1.83
    ोसिएशन
    1.81
    Activations Density 1.743%

    No Known Activations