© 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. 80887
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    c
    0.56
    l
    0.56
    p
    0.55
    әр
    0.46
    tn
    0.46
    raz
    0.46
    rek
    0.45
    ç
    0.44
     సాం
    0.44
    lok
    0.43
    POSITIVE LOGITS
     interferon
    0.65
     gallium
    0.60
     germanium
    0.58
     enzymes
    0.56
     pigments
    0.55
     blueberries
    0.55
     kinases
    0.55
     uridine
    0.55
     divalent
    0.55
     catalysts
    0.54
    Activations Density 0.000%

    No Known Activations