© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 9625
    Prev
    Next
    INDEX
    Explanations

    task list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    什么的
    0.31
    лер
    0.30
     finely
    0.30
     ál
    0.30
    amples
    0.29
     paramagnetic
    0.29
     എന്നിവ
    0.29
     đ
    0.29
     methylene
    0.29
     ३
    0.29
    POSITIVE LOGITS
     called
    0.46
    たちが
    0.41
     bernama
    0.40
     जिसने
    0.39
     that
    0.39
     που
    0.39
     being
    0.38
     having
    0.38
     chamado
    0.38
     چې
    0.38
    Activations Density 0.001%

    No Known Activations