© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13580
    Prev
    Next
    INDEX
    Explanations

    washing and cleaning the face

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

    The neuron is detecting numeric tokens and measurements (digits, decimals, and quantities).

    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
    کاری
    0.59
     યોગ
    0.58
    ahankan
    0.57
     ट्रांस
    0.57
    🩰
    0.57
     Тран
    0.56
     Acupuncture
    0.55
     द्वी
    0.55
    对称
    0.55
     অ্যাম
    0.54
    POSITIVE LOGITS
     washing
    1.72
    洗
    1.70
     wash
    1.70
     Washing
    1.64
     soap
    1.57
     Wash
    1.57
     washes
    1.56
     WASH
    1.48
    washing
    1.47
    Wash
    1.47
    Activations Density 0.430%

    No Known Activations