© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7527
    Prev
    Next
    INDEX
    Explanations

    temperature units and measurements

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

    The neuron strongly activates on occurrences of the word “degree,” especially in measurement‐style phrases (e.g. “degree of overlap,” “degree of estimation”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stranger
    0.59
    ENA
    0.56
    idental
    0.54
    棘
    0.53
    ခြင်း
    0.52
    rdquo
    0.50
     Eben
    0.50
     LEC
    0.50
    ⑭
    0.50
     Squire
    0.49
    POSITIVE LOGITS
     सेल्सियस
    0.80
    Celsius
    0.80
     degrees
    0.77
     Fahrenheit
    0.75
    }°
    0.74
     Celsius
    0.71
    GREES
    0.71
    degrees
    0.69
     derece
    0.69
     டிகிரி
    0.68
    Activations Density 0.200%

    No Known Activations