© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8809
    Prev
    Next
    INDEX
    Explanations

    svg code begins

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    arctic
    0.80
     Equation
    0.75
     каттоосуз
    0.75
     IIT
    0.72
     IDENT
    0.72
     parum
    0.71
     Á
    0.71
     가
    0.70
     planen
    0.69
    ப்பி
    0.69
    POSITIVE LOGITS
    嚇
    0.73
    Wen
    0.73
    лять
    0.71
    最終
    0.70
     बनाये
    0.69
    χι
    0.69
    𝙤
    0.69
    ussi
    0.68
    oura
    0.68
    Tray
    0.67
    Activations Density 0.002%

    No Known Activations