© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6188
    Prev
    Next
    INDEX
    Explanations

    temperature related words

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

    This neuron responds strongly to the word “hot” (including compounds like “hot-spot” and “hot-rod”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "hot" when it appears as part of compound terms or phrases, particularly in technical contexts, brand names, or idiomatic expressions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    terms denoting heat or warmth, including temperature-related language, compounds, and metaphorical “hot” usages.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     waved
    0.60
     fein
    0.59
     Shant
    0.59
     diagn
    0.56
     frightening
    0.56
    rang
    0.55
     diag
    0.55
    reng
    0.55
    桀
    0.55
     dasar
    0.53
    POSITIVE LOGITS
     hot
    1.36
    Hot
    1.32
     HOT
    1.30
     hotter
    1.29
    热
    1.27
    hot
    1.23
     गर्म
    1.22
    HOT
    1.21
     Hot
    1.18
     热
    1.17
    Activations Density 0.180%

    No Known Activations