© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7373
    Prev
    Next
    INDEX
    Explanations

    don't overdo it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     पिक्चर
    0.88
    <0x81>
    0.85
     మర
    0.83
    карбо
    0.83
    so
    0.80
    udades
    0.79
    eney
    0.79
    onej
    0.78
    弱
    0.77
    weak
    0.76
    POSITIVE LOGITS
     ओनली
    1.06
     rationale
    1.02
    JlcG
    0.98
    Jlc
    0.97
     형태로
    0.97
     식으로
    0.96
    stringProp
    0.94
     일이
    0.93
     blaster
    0.92
     형태
    0.92
    Activations Density 0.013%

    No Known Activations