© 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. 111085
    Prev
    Next
    INDEX
    Explanations

    seasons, weather, and natural events

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

    The neuron spotlights mentions of weather or environmental conditions—especially words about drought, seasonal extremes, runoff, and related climate events.

    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
    鲠
    -1.25
    匾
    -1.23
    すすめ
    -1.21
    anzug
    -1.17
     granit
    -1.17
    volles
    -1.17
     różnych
    -1.16
     universite
    -1.16
     puppets
    -1.13
    étit
    -1.13
    POSITIVE LOGITS
     last
    1.70
     volverá
    1.38
     enough
    1.35
     are
    1.32
     time
    1.31
     comenzará
    1.30
     due
    1.30
     will
    1.27
     in
    1.27
     Really
    1.24
    Activations Density 0.053%

    No Known Activations