© 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. 59320
    Prev
    Next
    INDEX
    Explanations

    weather descriptions, conditions

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

    The neuron activates strongly on descriptive weather–related adjectives (e.g. “bad,” “dreadful,” “warm”) and their context.

    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
    emis
    -0.74
     Odor
    -0.70
     зимой
    -0.66
     子供
    -0.66
     ночью
    -0.65
    界面
    -0.65
     durante
    -0.65
    victory
    -0.63
     чого
    -0.63
    Є
    -0.63
    POSITIVE LOGITS
     weather
    7.31
    weather
    5.19
    Weather
    4.75
     Weather
    4.66
     WEATHER
    4.28
    WEATHER
    3.97
    天气
    3.36
     météo
    2.89
     пого
    2.89
    天氣
    2.66
    Activations Density 0.058%

    No Known Activations