© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99402
    Prev
    Next
    INDEX
    Explanations

    Heat plus associated processes

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

    The neuron strongly responds to occurrences of the standalone term “Heat,” especially when it appears as part of headings or technical phrases.

    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
    漏れ
    -0.96
    鈴
    -0.84
     hình
    -0.84
    യി
    -0.83
    ouncer
    -0.83
    turbo
    -0.82
    plink
    -0.81
     Naruto
    -0.80
    cq
    -0.79
     jugo
    -0.78
    POSITIVE LOGITS
     exchanger
    1.28
    wave
    1.27
    stroke
    1.15
     exchangers
    1.09
    hland
    1.06
    hlands
    0.99
     време
    0.99
     🔥
    0.99
    lh
    0.93
     tenté
    0.93
    Activations Density 0.021%

    No Known Activations