© 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. 81048
    Prev
    Next
    INDEX
    Explanations

    list analysis, word properties, technical terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    邕
    0.46
     Coss
    0.45
     විශ්
    0.43
     visualized
    0.42
    С
    0.42
    ப்பிர
    0.42
     depicts
    0.41
     North
    0.41
    στ
    0.40
    ꞌ
    0.40
    POSITIVE LOGITS
    нков
    0.48
     nebude
    0.45
     शुर
    0.41
    די
    0.40
    แกรม
    0.40
    冭
    0.40
     dovrà
    0.40
    Sentiment
    0.40
    πτυ
    0.38
     måtte
    0.38
    Activations Density 0.007%

    No Known Activations