© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7212
    Prev
    Next
    INDEX
    Explanations

    water

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

    The neuron strongly activates on occurrences of the string “water” (in any casing or compound form).

    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
    삭
    0.66
    纬
    0.59
     growth
    0.56
    来源
    0.55
    Gregory
    0.55
     ventricle
    0.54
     Continuing
    0.53
    ट्र
    0.52
    0.52
     downturn
    0.52
    POSITIVE LOGITS
    💧
    0.93
    💦
    0.88
    melon
    0.88
    的水
    0.86
     Water
    0.83
     水
    0.79
    logged
    0.76
     Agua
    0.76
     Wasser
    0.76
     água
    0.74
    Activations Density 0.182%

    No Known Activations