© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56655
    Prev
    Next
    INDEX
    Explanations

    degrees C and temperature range

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

    The neuron fires on numerical temperature references—numeric values and units (especially Celsius/Fahrenheit) describing measured temperatures.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    雨
    -0.90
    谥
    -0.87
    size
    -0.86
    ObjectMeta
    -0.84
    Halloween
    -0.81
    ométrie
    -0.81
     雨
    -0.80
    LookAnd
    -0.80
    cinated
    -0.79
    uſ
    -0.77
    POSITIVE LOGITS
     temperature
    3.81
     temperatures
    3.53
     Temperature
    2.98
    temperature
    2.95
    Temperature
    2.80
     Temperatures
    2.73
     thermometer
    2.58
     temperatura
    2.47
     Celsius
    2.39
     temperaturas
    2.38
    Activations Density 0.103%

    No Known Activations