© 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-262K
    7. 5928
    Prev
    Next
    INDEX
    Explanations

    contrasts, timeframes, or counterpoints

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     괜찮
    0.88
    不够
    0.81
     ayarl
    0.78
     चांगली
    0.77
     wieder
    0.75
    tilde
    0.75
     يا
    0.73
    widetilde
    0.73
    常用的
    0.72
    स
    0.71
    POSITIVE LOGITS
     Despite
    1.60
     despite
    1.38
    Despite
    1.35
     controversies
    1.26
    despite
    1.25
     Generations
    1.17
     generations
    1.08
     Ironically
    1.08
     centuries
    1.08
     decades
    1.07
    Activations Density 0.299%

    No Known Activations