© 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. 135099
    Prev
    Next
    INDEX
    Explanations

    stronger verbs

    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
     Attitudes
    0.56
    ленное
    0.47
    hubung
    0.47
    婄
    0.46
     organisations
    0.46
    佶
    0.45
     एक्सपे
    0.45
    ohnt
    0.45
     Anywhere
    0.45
     Organisations
    0.44
    POSITIVE LOGITS
    as
    0.56
    to
    0.55
    u
    0.54
     meek
    0.53
    at
    0.52
     placer
    0.52
     labor
    0.50
    t
    0.50
     paralel
    0.49
     brisk
    0.49
    Activations Density 0.000%

    No Known Activations