© 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. 31-GEMMASCOPE-2-RES-262K
    7. 129276
    Prev
    Next
    INDEX
    Explanations

    language terms and descriptions

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    3
    0.64
    4
    0.57
    M
    0.55
    2
    0.54
    S
    0.51
    5
    0.51
    tr
    0.50
    D
    0.50
    1
    0.49
    i
    0.49
    POSITIVE LOGITS
     siquiera
    0.52
    흡
    0.46
     ފ
    0.45
     помощи
    0.45
     kür
    0.45
     конденса
    0.45
     notícias
    0.44
     والوں
    0.44
     preocupación
    0.44
    annah
    0.43
    Activations Density 0.004%

    No Known Activations