© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8969
    Prev
    Next
    INDEX
    Explanations

    rain and rainfall

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

    The neuron fires on words referring to heavy precipitation and storm-related rainfall.

    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
    d
    -2.09
    z
    -1.96
    f
    -1.95
    k
    -1.84
    >
    -1.83
    on
    -1.76
    p
    -1.74
     entanto
    -1.74
    in
    -1.73
    ay
    -1.73
    POSITIVE LOGITS
     vijf
    1.75
     exclusivamente
    1.73
     aleación
    1.60
    儅
    1.59
    ܊
    1.55
     comprando
    1.55
     vorige
    1.52
     bijzonder
    1.51
    푆
    1.48
     vengono
    1.45
    Activations Density 0.021%

    No Known Activations