© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1846
    Prev
    Next
    INDEX
    Explanations

    aspect or part of

    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_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
    ина
    1.12
     annuelle
    1.07
     silks
    0.93
    camiseta
    0.89
     junge
    0.89
     absoluta
    0.88
    asparagus
    0.88
    .*\
    0.88
     doméstica
    0.87
     রকমের
    0.87
    POSITIVE LOGITS
    ridge
    1.05
     tử
    1.05
    cially
    1.03
    ীদার
    0.98
    aking
    0.96
    AIN
    0.95
     mềm
    0.94
    endsWith
    0.93
    cip
    0.92
    ời
    0.92
    Activations Density 0.227%

    No Known Activations