© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    for free/custom/a

    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
    in
    0.30
    eers
    0.30
    I
    0.29
    ed
    0.29
    D
    0.28
    다면
    0.28
    ür
    0.27
    ম
    0.27
    en
    0.26
    em
    0.26
    POSITIVE LOGITS
     sake
    0.31
     purposes
    0.29
     produksi
    0.24
    ked
    0.23
     repurchase
    0.23
     residentes
    0.22
     production
    0.22
     a
    0.22
     resale
    0.21
     comparison
    0.21
    Activations Density 0.353%

    No Known Activations