© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10284
    Prev
    Next
    INDEX
    Explanations

    coconut milk

    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
    ्स
    2.28
    ا
    2.28
    い
    2.09
    ע
    2.05
    ુ
    2.05
    ाय
    1.84
    ಲ್ಲಿ
    1.84
    ع
    1.83
    icu
    1.80
    ेट
    1.80
    POSITIVE LOGITS
    m
    2.05
    w
    1.95
    n
    1.92
     Navigate
    1.80
     Blogs
    1.80
    d
    1.73
    wenden
    1.70
    r
    1.69
    st
    1.68
     Sanct
    1.65
    Activations Density 0.002%

    No Known Activations