© 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. 36326
    Prev
    Next
    INDEX
    Explanations

    claims

    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
     PRODUCT
    0.78
    (
    0.77
     transparent
    0.74
     brightly
    0.72
    ки
    0.70
     acqua
    0.68
     interrom
    0.67
    з
    0.67
    н
    0.67
    ﾒ
    0.67
    POSITIVE LOGITS
    ریشن
    1.02
     sintering
    0.96
    сным
    0.94
    ным
    0.92
    atsii
    0.90
     femora
    0.89
    ilization
    0.88
     MediaQuery
    0.88
     Ainda
    0.88
     Toxicology
    0.88
    Activations Density 0.000%

    No Known Activations