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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42012
    Prev
    Next
    INDEX
    Explanations

    genital warts, fistula, tract, system, diversity, cancer

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

    This neuron detects names of people, particularly in contexts related to medical or genital topics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on tokens containing the letter‐sequence “en” at the start (e.g. Jenna, Senna, genital).

    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
    鬟
    -3.28
    ーズン
    -2.97
    艄
    -2.88
    愎
    -2.77
    ’，
    -2.73
    ᜀ
    -2.72
    geſ
    -2.69
    懨
    -2.67
    ：
    -2.67
     její
    -2.67
    POSITIVE LOGITS
    ↵↵
    4.06
    _
    3.55
    :
    3.05
    ,
    2.95
    up
    2.89
    u
    2.73
    ).
    2.72
    n
    2.66
     …
    2.64
    |
    2.63
    Activations Density 0.043%

    No Known Activations