© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73007
    Prev
    Next
    INDEX
    Explanations

    deg or deg C

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

    The neuron activates on the substring “deg” when it appears as part of a measurement of degrees.

    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
    </i>
    -3.20
    ꯹
    -3.20
    ).
    -3.00
    槼
    -2.95
    衪
    -2.78
    ・・・」
    -2.67
    媗
    -2.67
    czema
    -2.64
    ेमाल
    -2.63
    orithm
    -2.55
    POSITIVE LOGITS
     '
    3.03
    *
    2.95
    </sup>
    2.92
    —
    2.66
    A
    2.50
     "
    2.50
    </h4>
    2.48
     If
    2.48
    If
    2.47
     américaine
    2.47
    Activations Density 0.001%

    No Known Activations