© 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. 3906
    Prev
    Next
    INDEX
    Explanations

    legislation governing laws

    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
    श
    2.09
    이자
    2.05
    ა
    2.03
    تان
    2.02
    з
    1.93
    мп
    1.84
    л
    1.84
    ंग
    1.83
    で
    1.77
    ्टी
    1.76
    POSITIVE LOGITS
    ни
    2.30
    ut
    2.27
    islation
    1.98
    is
    1.93
    id
    1.90
    it
    1.83
    are
    1.81
    <0x80>
    1.77
    носит
    1.74
     demikian
    1.72
    Activations Density 0.001%

    No Known Activations