© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6809
    Prev
    Next
    INDEX
    Explanations

    river and rivers

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

    The neuron activates on mentions of rivers and river‐related geographic or morphological terms.

    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
     সমুদ্র
    0.79
    海の
    0.73
    的海
    0.67
     моря
    0.66
     समुद्री
    0.63
     समुद्र
    0.60
     海
    0.59
    海
    0.59
     море
    0.57
     கடற்க
    0.57
    POSITIVE LOGITS
     river
    2.75
     River
    2.50
    River
    2.48
     riverside
    2.47
    river
    2.41
     RIVER
    2.33
     नदी
    2.23
    河
    2.20
    河流
    2.11
     sungai
    2.02
    Activations Density 0.612%

    No Known Activations