© 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. 5830
    Prev
    Next
    INDEX
    Explanations

    through banning, colder than, she stated

    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
     Cr
    0.40
     Shroff
    0.40
    壳
    0.38
     Cri
    0.37
     shell
    0.37
     Shell
    0.36
    殼
    0.35
     Bef
    0.35
     Bid
    0.35
     cries
    0.35
    POSITIVE LOGITS
    Percent
    0.43
    Percentages
    0.43
    Sqrt
    0.42
    okine
    0.42
    ריך
    0.41
     процент
    0.41
    CommandLine
    0.41
    <unused638>
    0.40
     transmutation
    0.40
    <unused343>
    0.39
    Activations Density 0.000%

    No Known Activations