© 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. 130017
    Prev
    Next
    INDEX
    Explanations

    guy and associated descriptions

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

    The neuron strongly activates on informal gendered address words—especially “guy” (and its plural “guys” or variants like “gals”).

    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
     übri
    -3.44
    “
    -3.17
    </em>
    -3.09
    踅
    -2.73
     gesamte
    -2.73
     heutige
    -2.69
     berühmten
    -2.66
    摃
    -2.64
    ஂ
    -2.61
    鈊
    -2.56
    POSITIVE LOGITS
    埽
    3.36
    𖣘
    2.94
    筇
    2.80
    🍺
    2.59
    ☆☆☆☆
    2.58
     varsa
    2.47
     />}
    2.45
    屺
    2.44
     ingat
    2.41
    ܜ
    2.41
    Activations Density 0.008%

    No Known Activations