© 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. 2220
    Prev
    Next
    INDEX
    Explanations

    variables and punctuation

    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
     infrastrukt
    0.44
     μας
    0.41
     awọn
    0.41
     \\..
    0.40
     jų
    0.40
     얼마나
    0.40
     reuniones
    0.39
     szczególnie
    0.39
    𒊑
    0.39
     irmãos
    0.39
    POSITIVE LOGITS
    a
    0.59
     consisting
    0.55
    an
    0.54
    t
    0.54
    c
    0.52
    U
    0.52
    at
    0.52
    A
    0.52
    Z
    0.51
    id
    0.51
    Activations Density 0.232%

    No Known Activations