© 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. 7315
    Prev
    Next
    INDEX
    Explanations

    Drying or taxing environments

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

    The neuron is a “wh-word” spotter – it lights up on question/relative pronouns like “which,” “what,” etc.

    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
     roupas
    0.78
     lágrimas
    0.77
     toprak
    0.76
     любом
    0.75
    ו
    0.75
     embraces
    0.74
     ganas
    0.74
    o
    0.73
     posl
    0.73
     sandals
    0.73
    POSITIVE LOGITS
     Drying
    0.82
    ни
    0.79
     taxing
    0.72
    cing
    0.68
     Alpes
    0.68
    <0x90>
    0.67
     nuisance
    0.67
     Thank
    0.66
     Ну
    0.65
     डैम
    0.65
    Activations Density 0.000%

    No Known Activations