© 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. 10-GEMMASCOPE-RES-131K
    7. 7981
    Prev
    Next
    INDEX
    Explanations

    isothermal processes and Olympia

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

    The neuron fires on occurrences of “isotherm” or “isothermal” (e.g., in phrases like moisture sorption isotherms or isothermal amplification).

    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
     tidak
    -2.52
     "
    -2.44
     They
    -2.33
    齶
    -2.27
    푇
    -2.20
     Each
    -2.17
     ”
    -2.17
     メニュー
    -2.17
    蓠
    -2.13
     Both
    -2.11
    POSITIVE LOGITS
    also
    2.77
    럿
    2.67
    e
    2.56
    냑
    2.33
    嶄
    2.27
    鱨
    2.27
     ſy
    2.22
     {
    2.20
    牐
    2.19
    ⬮
    2.16
    Activations Density 0.002%

    No Known Activations