© 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. 41979
    Prev
    Next
    INDEX
    Explanations

    Glasgow Coma Scale

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

    This neuron responds strongly to tokens that contain internal uppercase letters (e.g. CamelCase identifiers or all-caps acronyms).

    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
    3
    -3.17
    0
    -2.73
    6
    -2.66
    2
    -2.56
    4
    -2.36
    8
    -2.31
    5
    -2.25
    1
    -2.22
    </h5>
    -2.06
     querían
    -2.06
    POSITIVE LOGITS
    </strong>
    2.39
     также
    2.16
     Also
    1.83
     vœ
    1.77
    ⸂
    1.74
    orite
    1.66
     плани
    1.64
     iglesia
    1.64
     sorgen
    1.63
    蹋
    1.62
    Activations Density 0.001%

    No Known Activations