© 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. 9287
    Prev
    Next
    INDEX
    Explanations

    specific conditions

    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
     ingen
    0.41
    fl
    0.41
     सला
    0.41
    igl
    0.40
     annihil
    0.39
    เคลื่อน
    0.38
    wap
    0.37
    ']))->
    0.37
     voj
    0.37
     flamb
    0.37
    POSITIVE LOGITS
     Electric
    0.46
    Ри
    0.46
    icited
    0.45
     spécifique
    0.43
    Ві
    0.43
     elétrica
    0.42
    Автор
    0.41
     livelli
    0.41
    :<
    0.41
    Демо
    0.41
    Activations Density 0.006%

    No Known Activations