© 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. 45422
    Prev
    Next
    INDEX
    Explanations

    Milton, Aitken, Increased, Statin, Donate

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

    This neuron specifically responds to occurrences of the proper name “Milton.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     bestimmte
    -2.83
    各样的
    -2.67
     bekannte
    -2.55
    今では
    -2.55
     přístup
    -2.52
    偌
    -2.50
    少ない
    -2.47
     общей
    -2.42
     klassische
    -2.39
     eighteen
    -2.38
    POSITIVE LOGITS
    
    3.70
    齮
    2.80
    n
    2.78
    薆
    2.72
    ⎔
    2.56
    蟶
    2.53
    玊
    2.44
    enablog
    2.41
    釭
    2.41
    your
    2.39
    Activations Density 0.001%

    No Known Activations