Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8863
    Prev
    Next
    INDEX
    Explanations

    temperature and weather

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    的人都
    -0.75
    abaret
    -0.75
     defiance
    -0.71
     launder
    -0.67
     निम्न
    -0.66
    ⚠
    -0.66
    Tropical
    -0.66
     OGSÅ
    -0.65
     Valuation
    -0.64
    ाउन
    -0.64
    POSITIVE LOGITS
     temperature
    2.69
     humidity
    1.94
     wind
    1.89
     Temperature
    1.89
    temperature
    1.77
     temperatures
    1.63
    Temperature
    1.57
     atmospheric
    1.49
     pressure
    1.41
     TEMPERATURE
    1.37
    Activations Density 0.047%

    No Known Activations