© 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. 11855
    Prev
    Next
    INDEX
    Explanations

    cold

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

    The neuron activates on words describing temperature conditions (e.g. “chilly,” “frigid,” “icy,” “cold,” “warmth”).

    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
     жар
    -1.08
    暖かい
    -1.01
    暑い
    -0.98
     warm
    -0.93
     hotter
    -0.92
    Heat
    -0.92
    ласти
    -0.90
     overheat
    -0.88
     sunny
    -0.87
    Warm
    -0.86
    POSITIVE LOGITS
     cold
    3.33
    cold
    2.86
     Cold
    2.75
    Cold
    2.64
     COLD
    2.55
    COLD
    2.27
     холод
    2.17
     icy
    2.14
     coldness
    1.99
     chilly
    1.98
    Activations Density 0.038%

    No Known Activations