© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30945
    Prev
    Next
    INDEX
    Explanations

    global warming average

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

    The neuron is keyed to numeric date and measurement tokens—especially years and related climate‐data figures (e.g. “2017,” “second hottest year,” “global temperature”).

    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
    Kön
    -0.78
    高考
    -0.75
    Collapse
    -0.74
    balho
    -0.74
    kön
    -0.73
    ffold
    -0.72
     Pests
    -0.72
    Ύ
    -0.71
    gcd
    -0.71
    你就
    -0.71
    POSITIVE LOGITS
     warming
    1.36
     average
    1.30
     global
    1.23
     warm
    1.19
     warmer
    1.17
     warmest
    1.16
     Average
    1.14
     Warm
    1.12
    Average
    1.07
    average
    1.03
    Activations Density 0.030%

    No Known Activations