© 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. 22-GEMMASCOPE-RES-131K
    7. 33248
    Prev
    Next
    INDEX
    Explanations

    user and guide

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

    The neuron fires on any occurrence of the substring “user” (e.g. “user,” “users,” or “usr” in file-path tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ’
    -3.77
     they
    -2.97
    y
    -2.69
    ",
    -2.61
    x
    -2.39
    最重要的
    -2.25
    絰
    -2.25
     probablement
    -2.20
    ,.
    -2.20
     sont
    -2.20
    POSITIVE LOGITS
    𖣘
    2.80
     Their
    2.64
    𖡼
    2.52
    เกง
    2.52
    
    2.48
    沇
    2.45
    ࿚
    2.39
    噥
    2.38
    鯔
    2.34
    塤
    2.34
    Activations Density 0.060%

    No Known Activations