© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38368
    Prev
    Next
    INDEX
    Explanations

    Pro bowler names and places Pro bowler names and places

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects proper-noun entity tokens (names of people, places, organizations, or other titled/unique terms).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
    秾
    -1.75
    酹
    -1.74
    ();
    -1.55
    gencias
    -1.54
    踯
    -1.51
    㩒
    -1.50
     your
    -1.48
    licante
    -1.46
    诓
    -1.45
    </b>
    -1.43
    POSITIVE LOGITS
    
    1.54
     there
    1.48
    兩種
    1.47
     таким
    1.38
     entregar
    1.36
     if
    1.34
    caucasian
    1.30
    [
    1.28
     If
    1.27
     żołnier
    1.27
    Activations Density 0.055%

    No Known Activations