© 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. 22-GEMMASCOPE-RES-131K
    7. 54516
    Prev
    Next
    INDEX
    Explanations

    programming code

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

    The neuron fires on numeric literals (multi‐digit numbers) embedded 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_22/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
    serviceWorker
    -1.18
    hallen
    -1.00
     as
    -0.99
     memen
    -0.96
    áfrica
    -0.96
     évek
    -0.95
    entait
    -0.94
    :+:
    -0.93
    Incluso
    -0.92
    ":
    -0.91
    POSITIVE LOGITS
     tramonto
    1.02
     mattino
    0.88
    就会
    0.88
     jbl
    0.86
     understands
    0.86
     verschill
    0.86
     zoveel
    0.85
    有点
    0.84
     dreapta
    0.84
     bepaald
    0.84
    Activations Density 0.021%

    No Known Activations