© 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. 40-GEMMASCOPE-2-RES-262K
    7. 3154
    Prev
    Next
    INDEX
    Explanations

    code comments following punctuation

    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/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    glb
    0.39
    ।’’
    0.38
     giấc
    0.36
    dif
    0.35
    Universal
    0.35
    GoAbroad
    0.35
    abin
    0.34
    कान
    0.33
    ODBA
    0.33
    牌
    0.33
    POSITIVE LOGITS
     vi
    0.48
     خل
    0.39
    చారం
    0.38
     Kode
    0.38
     fut
    0.37
     Alf
    0.37
     pokemon
    0.37
     AW
    0.37
     xia
    0.37
     مطلب
    0.36
    Activations Density 0.002%

    No Known Activations