© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15651
    Prev
    Next
    INDEX
    Explanations

    dental care and teeth brushing

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

    The neuron strongly responds to marketing‐style pitches offering ready-made image or drawing collections (e.g. “get a collection of mood-boosting picture drawings”).

    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
    correo
    0.64
    irting
    0.61
    Acetyl
    0.60
    лянчук
    0.58
    蛸
    0.57
     швидко
    0.57
     hurriedly
    0.56
    线路
    0.55
    Correo
    0.55
    閭
    0.55
    POSITIVE LOGITS
     aesthetic
    0.70
     orthodontic
    0.61
     sculptural
    0.59
     images
    0.58
     colors
    0.58
     showcases
    0.57
     Sculpture
    0.57
     orthodont
    0.56
     aesthetics
    0.55
     showcase
    0.55
    Activations Density 0.015%

    No Known Activations