© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60323
    Prev
    Next
    INDEX
    Explanations

    Ash names and places

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

    The neuron selectively activates on the substring “Ash” within proper 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_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
    ⩴
    -3.20
    of
    -2.83
    ’-
    -2.80
    禤
    -2.78
     ,‬
    -2.67
    ブログ村
    -2.56
    榦
    -2.56
    ’?
    -2.56
    ”，
    -2.55
    ’)
    -2.55
    POSITIVE LOGITS
    {
    3.36
    珦
    2.92
    s
    2.88
    --
    2.67
    The
    2.61
     What
    2.61
    鈇
    2.52
     If
    2.48
     This
    2.47
    ;
    2.44
    Activations Density 0.002%

    No Known Activations