© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68990
    Prev
    Next
    INDEX
    Explanations

    class, type and generic declarations

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

    The neuron is triggered by numeric literals—tokens representing numbers (integers or floats) in the 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
     macetas
    -1.86
    犼
    -1.77
     inversiones
    -1.77
     bicicletas
    -1.63
     faldas
    -1.62
     proveedores
    -1.58
     productos
    -1.58
     botellas
    -1.55
     tarifas
    -1.52
     licencias
    -1.52
    POSITIVE LOGITS
     of
    5.25
     questionSearch
    1.39
    avait
    1.37
     PROSPECT
    1.32
     for
    1.32
     certaines
    1.31
     barnet
    1.31
    </sub>
    1.30
    </h1>
    1.30
     auffi
    1.27
    Activations Density 0.014%

    No Known Activations