© 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. 1281
    Prev
    Next
    INDEX
    Explanations

    love, accession, and specific accent

    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
    وش
    0.54
    忝
    0.53
    㐫
    0.52
    aring
    0.48
    وسف
    0.45
     ठहर
    0.44
    濰
    0.44
    There
    0.44
     Persever
    0.44
    وشی
    0.44
    POSITIVE LOGITS
     that
    0.48
     vocal
    0.47
    Nuestro
    0.44
     OUT
    0.43
    ↵↵
    0.42
     coconut
    0.41
    נם
    0.41
     sin
    0.41
     outrage
    0.41
     nautical
    0.41
    Activations Density 0.000%

    No Known Activations