© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90609
    Prev
    Next
    INDEX
    Explanations

    water bodies

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

    This neuron detects occurrences of the word “water” (i.e. mentions of bodies or instances of water).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    as
    -1.61
     jene
    -1.60
     esigen
    -1.59
    EN
    -1.57
     الثالث
    -1.48
    」
    -1.48
     وست
    -1.47
    J
    -1.45
     accompagn
    -1.45
     dott
    -1.44
    POSITIVE LOGITS
    ICIENCY
    1.60
     wavering
    1.50
     ständig
    1.49
    ка
    1.45
     drooping
    1.41
     claras
    1.34
     ด้วย
    1.34
     gezet
    1.34
    Leírás
    1.34
    impôt
    1.33
    Activations Density 0.020%

    No Known Activations