© 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. 129247
    Prev
    Next
    INDEX
    Explanations

    foreign characters 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
    l
    0.50
     =
    0.50
     '
    0.48
     "
    0.48
     sepsis
    0.47
     '.
    0.47
     --
    0.47
    ".
    0.45
     ".
    0.45
     bestimmten
    0.44
    POSITIVE LOGITS
    ńskiej
    0.45
    iziert
    0.45
     घोड़े
    0.45
    녔
    0.45
    篪
    0.44
    itatud
    0.44
    azi
    0.44
    owanej
    0.44
    ார்க்க
    0.43
     سنة
    0.43
    Activations Density 0.002%

    No Known Activations