© 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. 10-GEMMASCOPE-RES-131K
    7. 60047
    Prev
    Next
    INDEX
    Explanations

    temperature dependence and range

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

    The neuron strongly activates on the word “Temperature” (e.g. as a heading or parameter name) wherever it appears.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    s
    -3.31
    是
    -3.25
    '
    -3.23
    𖣘
    -2.92
     但
    -2.81
    没有
    -2.73
    ふた
    -2.72
    仅
    -2.69
    眼睛
    -2.63
     当
    -2.61
    POSITIVE LOGITS
    .
    4.06
    趼
    3.47
    ↵
    3.47
    ⽌
    3.38
    轫
    3.08
    犇
    2.98
    閎
    2.73
    飏
    2.66
    锜
    2.66
    
    2.64
    Activations Density 0.011%

    No Known Activations