© 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-65K
    7. 7918
    Prev
    Next
    INDEX
    Explanations

    import React statements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     {
    0.94
    lassen
    0.85
    тта
    0.85
     ={
    0.84
    दाय
    0.83
    らは
    0.80
    ക്കിയത്
    0.80
    idze
    0.79
    novu
    0.79
    [{
    0.77
    POSITIVE LOGITS
     pedestrian
    0.70
     sidew
    0.70
     concluding
    0.68
     anticipating
    0.68
     sounding
    0.68
     사용할
    0.68
    .'"
    0.67
     noting
    0.66
     '"
    0.66
     discerning
    0.66
    Activations Density 0.002%

    No Known Activations