© 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. 22-GEMMASCOPE-RES-131K
    7. 25566
    Prev
    Next
    INDEX
    Explanations

    high temperatures and heat

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

    The neuron detects references to high‐temperature or thermal conditions (e.g., words like boiling, heat, thermal, hot, molten, temperature, °C).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     viewDidLoad
    -1.10
     mètre
    -1.08
    Kult
    -1.07
    Garten
    -1.05
    ローラー
    -1.05
    TestingModule
    -1.05
     Coleridge
    -1.00
     вечера
    -1.00
     RIVERS
    -1.00
    лія
    -0.99
    POSITIVE LOGITS
     heating
    1.32
     heat
    1.24
     heated
    1.20
    ♨
    1.17
     temperature
    1.12
     熱
    1.11
     nóng
    1.09
    熱
    1.06
     hot
    1.05
    heated
    1.04
    Activations Density 0.077%

    No Known Activations