© 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. 34-GEMMASCOPE-RES-131K
    7. 93563
    Prev
    Next
    INDEX
    Explanations

    names starting with Fai or Fay

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

    The neuron fires on tokens that are parts of capitalized proper names beginning with “F,” e.g. Fay, Faye, Fajardo, Faiz, Fysek.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     هزینه
    -0.91
    ㅅ
    -0.77
     enthält
    -0.77
     contiene
    -0.76
     функций
    -0.74
    isir
    -0.73
    १
    -0.72
    dası
    -0.70
    ショップ
    -0.69
     съдържа
    -0.69
    POSITIVE LOGITS
     fay
    1.01
     Fay
    0.99
    Fay
    0.80
     ACCOM
    0.79
    Fai
    0.77
     Mé
    0.77
    fay
    0.77
     Kot
    0.76
     commodities
    0.75
     Tiny
    0.75
    Activations Density 0.015%

    No Known Activations