© 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. 65855
    Prev
    Next
    INDEX
    Explanations

    temperatures in celsius

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

    The neuron primarily activates on the degree symbol (°) used in temperature notations.

    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
    瀦
    -2.91
    彞
    -2.38
    rogates
    -2.36
    齷
    -2.34
    りますが
    -2.31
    وضوع
    -2.30
    ጴ
    -2.27
     gewöhnlich
    -2.23
    ります
    -2.22
    receta
    -2.19
    POSITIVE LOGITS
    ↵
    3.03
     of
    2.80
    .,
    2.78
    ',
    2.73
    ,'
    2.58
     we
    2.53
    いい
    2.39
    an
    2.38
    >
    2.30
    ’
    2.28
    Activations Density 0.005%

    No Known Activations