© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2322
    Prev
    Next
    INDEX
    Explanations

    law and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    ഊ
    0.78
     legales
    0.77
     मुखिया
    0.75
     tille
    0.70
    ގ
    0.70
     Cæ
    0.70
    ুরের
    0.69
     Modes
    0.69
     ino
    0.68
    뢨
    0.68
    POSITIVE LOGITS
     enforcement
    1.07
    suits
    0.97
     Enforcement
    0.96
    matig
    0.86
    giver
    0.86
    suit
    0.85
    makers
    0.83
    making
    0.81
    book
    0.76
    maker
    0.73
    Activations Density 0.164%

    No Known Activations