© 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. 9594
    Prev
    Next
    INDEX
    Explanations

    list of dictionarieslist of objectslist of lists

    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
    養
    0.46
     portas
    0.42
    ائض
    0.41
     مزید
    0.41
     স্নাত
    0.40
     inder
    0.39
     OXIDES
    0.39
    BOUR
    0.39
     restauración
    0.38
     kinderen
    0.38
    POSITIVE LOGITS
    ass
    0.50
    null
    0.47
    *,
    0.46
    {},
    0.45
    ˆ‚
    0.44
    item
    0.44
    ^{
    0.42
     "",
    0.42
    ri
    0.42
    ola
    0.41
    Activations Density 0.050%

    No Known Activations