© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9303
    Prev
    Next
    INDEX
    Explanations

    Silicon Valley

    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
    ا
    2.64
    ्स
    2.22
    锕
    1.97
    ৪
    1.92
    ıya
    1.87
    gica
    1.81
    を除く
    1.80
    tól
    1.80
    oğlu
    1.78
    LLER
    1.77
    POSITIVE LOGITS
    n
    1.95
    m
    1.90
    ش
    1.84
    م
    1.76
     defunct
    1.73
     dreaded
    1.71
    ف
    1.64
     monsieur
    1.63
     डाइऑक्साइड
    1.63
    TLE
    1.61
    Activations Density 0.002%

    No Known Activations