© 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. 74700
    Prev
    Next
    INDEX
    Explanations

    ! directives and code blocks

    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
     espécies
    0.48
     Metall
    0.46
     agricultura
    0.45
    癃
    0.44
     terroir
    0.44
     quantidade
    0.43
     superficie
    0.43
     commemorated
    0.43
     silicate
    0.42
     motoc
    0.42
    POSITIVE LOGITS
    puts
    0.42
    fig
    0.40
    beqz
    0.40
    "><?
    0.39
    epan
    0.38
    hab
    0.38
    declare
    0.38
    parent
    0.38
    pus
    0.38
    bun
    0.38
    Activations Density 0.001%

    No Known Activations