© 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. 10451
    Prev
    Next
    INDEX
    Explanations

    rooster cocks gallo ayam

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

    The neuron strongly activates on the word “cock” (including its literal form “rooster” and its slang/plural forms).

    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
    ?
    -2.52
    {
    -2.11
    .
    -2.08
    ;
    -1.84
    O
    -1.82
    T
    -1.76
     vores
    -1.75
    b
    -1.72
     otra
    -1.70
    ÑOS
    -1.69
    POSITIVE LOGITS
    iteľ
    1.90
    喈
    1.88
    夀
    1.87
    ۰۱
    1.81
    ONESIA
    1.79
     máme
    1.77
    Tarif
    1.77
    desertcart
    1.74
     Bestellung
    1.73
     ガラス
    1.71
    Activations Density 0.011%

    No Known Activations