© 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. 43555
    Prev
    Next
    INDEX
    Explanations

    words starting with Bod

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

    The neuron is keyed to any occurrence of the character sequence “bod” at the start of a token.

    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
    zelfde
    -2.72
    蟥
    -2.70
    CONSIN
    -2.67
     musí
    -2.56
    vantaged
    -2.56
     otoño
    -2.47
    CHREIBUNG
    -2.45
     Pantalla
    -2.41
     invierno
    -2.41
    which
    -2.41
    POSITIVE LOGITS
    {
    3.00
    P
    2.92
    
    2.86
    /
    2.73
    ↵↵
    2.73
    V
    2.73
    *
    2.69
    s
    2.63
    H
    2.59
    G
    2.58
    Activations Density 0.003%

    No Known Activations