© 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. 10388
    Prev
    Next
    INDEX
    Explanations

    people and things

    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
    ه
    0.47
     charms
    0.46
     colo
    0.43
    ▫
    0.42
    ag
    0.42
    FT
    0.42
     భాగంగా
    0.42
     amu
    0.41
    অ
    0.41
     pins
    0.41
    POSITIVE LOGITS
    izes
    0.46
    fueled
    0.45
    ዬ
    0.43
    på
    0.43
     Gaye
    0.42
     negras
    0.42
    stvo
    0.41
    ז
    0.41
     cuyas
    0.41
    centered
    0.41
    Activations Density 0.385%

    No Known Activations