© 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. 5127
    Prev
    Next
    INDEX
    Explanations

    rivers and geographies

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

    The neuron strongly activates on proper‐noun mentions of rivers and related geographic water bodies.

    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
    ולוג
    0.71
     unjust
    0.71
    ደን
    0.70
     кг
    0.69
     абсолютно
    0.69
     WEIGHT
    0.69
    <unused17>
    0.67
     LoginPage
    0.67
     VERT
    0.66
     stargazerCount
    0.66
    POSITIVE LOGITS
     tributaries
    1.12
     River
    0.93
     channel
    0.92
     tributary
    0.92
     Basin
    0.91
    川
    0.89
     river
    0.88
    River
    0.84
     inlets
    0.84
     rapids
    0.83
    Activations Density 0.303%

    No Known Activations