© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11326
    Prev
    Next
    INDEX
    Explanations

    logic gates and binary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    sers
    1.40
    disciplinary
    1.38
    <unused285>
    1.36
    वेत
    1.36
     настоящий
    1.34
    ቸውን
    1.34
    <unused292>
    1.33
    র
    1.31
     общество
    1.30
     реки
    1.28
    POSITIVE LOGITS
     ina
    1.13
    ting
    1.12
    हारिक
    1.08
     Paly
    1.05
    randint
    1.05
    ÁN
    1.03
     dosy
    1.02
     zů
    1.02
    liği
    1.01
    ంప
    1.01
    Activations Density 0.000%

    No Known Activations