© 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. 11012
    Prev
    Next
    INDEX
    Explanations

    accompanying warrant, documentation, diagrams, blog, image

    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
    ت
    1.59
    ות
    1.55
    ים
    1.45
    ો
    1.35
    ا
    1.32
    tä
    1.30
    ö
    1.30
    t
    1.30
    ු
    1.27
    tudo
    1.23
    POSITIVE LOGITS
     sidewalk
    1.11
     skillful
    1.11
     sharpen
    1.07
    যন্ত্র
    1.07
     Alka
    1.05
    ным
    1.05
    ствия
    1.02
    のだ
    1.00
     beaker
    1.00
     sharpening
    0.99
    Activations Density 0.002%

    No Known Activations