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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72966
    Prev
    Next
    INDEX
    Explanations

    Allison/Alison names

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

    The neuron primarily detects occurrences of the proper name “Allison” (including the variant “Alison”).

    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
    on
    -3.28
    ’
    -2.52
    you
    -2.52
    *
    -2.47
    of
    -2.44
     男人
    -2.33
    AL
    -2.31
    or
    -2.27
    V
    -2.17
    &
    -2.17
    POSITIVE LOGITS
    
    3.02
     AÑOS
    2.45
    𖧵
    2.42
    弖
    2.42
    涐
    2.39
    
    2.34
    纔
    2.31
    痾
    2.28
    他不
    2.28
    isation
    2.28
    Activations Density 0.003%

    No Known Activations