© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123967
    Prev
    Next
    INDEX
    Explanations

    distinguish from or tell apart

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    それにしても
    -1.54
     onPostExecute
    -1.37
     
    
    -1.35
    ﹍﹍
    -1.34
     you
    -1.31
    なぜか
    -1.27
    どうやら
    -1.27
    hedron
    -1.26
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.26
    お父
    -1.23
    POSITIVE LOGITS
     from
    1.27
     until
    1.20
     of
    1.17
    poň
    1.16
     are
    1.15
     Colleagues
    1.11
     schrij
    1.10
    ituri
    1.10
     Organize
    1.09
    ulihan
    1.09
    Activations Density 0.024%

    No Known Activations