© 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. 22-GEMMASCOPE-RES-131K
    7. 64629
    Prev
    Next
    INDEX
    Explanations

    titles and legal proceedings

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

    The neuron detects words used as formal titles or honorifics (e.g. forms of address, ranks, court names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.84
     neuen
    -1.62
     ersten
    -1.42
     nji
    -1.37
     otros
    -1.35
     Würde
    -1.34
    Exeunt
    -1.30
     Мекси
    -1.30
     algunos
    -1.27
    adá
    -1.26
    POSITIVE LOGITS
    s
    1.37
    ,
    1.26
    辊
    1.23
    ᠌
    1.23
     なし
    1.23
     esfuerzos
    1.17
    
    1.16
    [
    1.16
     runde
    1.15
     chini
    1.14
    Activations Density 0.001%

    No Known Activations