© 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. 34-GEMMASCOPE-RES-131K
    7. 686
    Prev
    Next
    INDEX
    Explanations

    weather, proper nouns

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

    This neuron detects meteorological forecast content—phrases and numbers associated with weather reports (e.g. cold fronts, dates, temperatures, storm names, and forecast timing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     pengetahuan
    -0.98
     }).
    -0.94
    getResources
    -0.90
     unpredictable
    -0.90
    天候
    -0.88
    흡
    -0.88
    据说
    -0.87
    ┍
    -0.87
     "}";
    -0.85
    ？！”
    -0.85
    POSITIVE LOGITS
     القص
    0.97
     mercredi
    0.94
     jeudi
    0.93
    决赛
    0.90
     afternoon
    0.90
     Moderate
    0.86
    Hence
    0.85
     maxime
    0.85
     बस
    0.85
    idespread
    0.84
    Activations Density 0.036%

    No Known Activations