© 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. 25250
    Prev
    Next
    INDEX
    Explanations

    celebrity surnames

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

    The neuron activates on the initial subword prefixes of capitalized personal 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
     in
    -2.06
     būt
    -1.66
     pirm
    -1.56
     at
    -1.53
     all
    -1.53
     with
    -1.52
     jūs
    -1.45
     from
    -1.43
     for
    -1.42
    ميل
    -1.30
    POSITIVE LOGITS
    耵
    1.68
    蛲
    1.29
    
    1.29
    筇
    1.29
    苼
    1.27
    ナメント
    1.27
    を行い
    1.26
    
    1.25
     accompagné
    1.24
    ౭
    1.24
    Activations Density 0.044%

    No Known Activations