© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7963
    Prev
    Next
    INDEX
    Explanations

    unsigned integer types like uint8_t

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

    This neuron detects fixed‐width integer type names (e.g. tokens like uint8_t, uint32_t, uint64_t) in code.

    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
    ......
    -2.03
    ....
    -1.98
     as
    -1.94
     ....
    -1.92
    .....
    -1.90
     but
    -1.89
    2
    -1.88
    .......
    -1.86
    ...."
    -1.81
     if
    -1.80
    POSITIVE LOGITS
     interieur
    1.91
     –
    1.86
    .
    1.84
     rafra
    1.78
     witte
    1.74
     coû
    1.74
     paillettes
    1.74
     goud
    1.74
     procha
    1.73
     ijs
    1.72
    Activations Density 0.003%

    No Known Activations