© 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. 38040
    Prev
    Next
    INDEX
    Explanations

    code snippets and data types

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

    The neuron fires on technical or code‐related identifiers—things like programming data types (e.g. “float”), file extensions (“.png”), URLs, version numbers, and other code tokens.

    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
    KOS
    -0.82
     først
    -0.79
     seja
    -0.78
     Repetition
    -0.71
    alos
    -0.71
    suchen
    -0.69
    anor
    -0.69
    Sheets
    -0.67
     ausgeschlossen
    -0.67
     المجلس
    -0.67
    POSITIVE LOGITS
     trailed
    0.71
    Jai
    0.68
    bund
    0.68
    htä
    0.67
     Schulte
    0.66
     Gol
    0.65
    shrink
    0.63
    Shrink
    0.61
    랜드
    0.61
    onLoad
    0.60
    Activations Density 0.077%

    No Known Activations