© 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. 34-GEMMASCOPE-RES-131K
    7. 34743
    Prev
    Next
    INDEX
    Explanations

    function definitions and calls

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

    This neuron detects tokens containing digits or numeric literals (e.g. version numbers, sizes, numeric type names, numeric constants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    いろいろ
    -0.85
    exemple
    -0.82
     voluntarios
    -0.80
     considérer
    -0.79
    Colore
    -0.79
     marqués
    -0.79
    wanna
    -0.79
    馀
    -0.78
     réserver
    -0.78
     maintenir
    -0.77
    POSITIVE LOGITS
     function
    2.55
     func
    2.27
     functions
    2.20
    Func
    2.11
    func
    2.06
    函数
    2.03
     функ
    2.00
    function
    1.84
     callback
    1.75
     fun
    1.73
    Activations Density 0.069%

    No Known Activations