© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11825
    Prev
    Next
    INDEX
    Explanations

    female names

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

    The neuron detects author bylines—i.e. the personal names (like “Mary F. Foskett”) that follow “By” in a text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wallpapers
    0.63
     murals
    0.59
    Wallpaper
    0.59
     Champions
    0.57
     Chag
    0.56
    җ
    0.55
     Wallpaper
    0.55
     wallpaper
    0.54
     répét
    0.54
    ಡುವುದ
    0.54
    POSITIVE LOGITS
    м
    0.70
    beth
    0.64
     Immaculate
    0.64
    sville
    0.63
    сль
    0.63
    am
    0.61
     Shelly
    0.61
    टाइम
    0.60
    у
    0.60
     liggen
    0.60
    Activations Density 0.039%

    No Known Activations