© 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. 34-GEMMASCOPE-RES-131K
    4. 55859
    Prev
    Next
    INDEX
    Explanations

    code definitions and returns

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

    The neuron specializes in spotting numeric literals (e.g. standalone numbers or constants) 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_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
     bohater
    -0.77
     trabajó
    -0.75
    izzate
    -0.74
    ént
    -0.73
    ᵎ
    -0.73
     сча
    -0.73
     démarrage
    -0.72
     preguntó
    -0.71
     sirvió
    -0.71
     oficjal
    -0.70
    POSITIVE LOGITS
     (
    1.39
     (
    
    1.22
    )(
    0.80
    …(
    0.79
     augmentation
    0.79
    тельства
    0.76
     типов
    0.76
     Eq
    0.75
     Eqs
    0.75
     .(
    0.75
    Activations Density 0.004%

    No Known Activations