© 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. 1047
    Prev
    Next
    INDEX
    Explanations

    data, information, and substances

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

    The neuron detects explicit mentions of drinking water (especially quantified water intake) in the 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_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
    ه
    0.83
    ে
    0.81
    i
    0.79
    ز
    0.74
     પાસે
    0.72
     Universitario
    0.71
     majorité
    0.70
     Ticket
    0.69
    的值
    0.69
    و
    0.69
    POSITIVE LOGITS
     nourishment
    1.02
     hydrate
    0.88
     hydrates
    0.88
     সরবরাহ
    0.86
     evaporation
    0.85
     hydration
    0.85
     nutrients
    0.84
    thirsty
    0.84
     transpiration
    0.82
     troughs
    0.81
    Activations Density 0.039%

    No Known Activations