© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1006
    Prev
    Next
    INDEX
    Explanations

    leads to more/fewer/greater

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

    This neuron detects definitional or explanatory “means/is” linking words (e.g. “means,” “is,” “mean”).

    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_24_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
     gồm
    0.82
     radiates
    0.74
     attir
    0.74
    ﺭ
    0.72
     sier
    0.71
    .")
    0.70
     Enzymes
    0.70
     אל
    0.70
    মনে
    0.70
    ようになる
    0.70
    POSITIVE LOGITS
    ش
    0.86
    وا
    0.80
    不再
    0.79
    ت
    0.77
     тысячи
    0.77
    ست
    0.75
    停车
    0.75
     فترة
    0.75
     verificación
    0.75
     принятия
    0.74
    Activations Density 0.037%

    No Known Activations