© 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. 10-GEMMASCOPE-RES-131K
    7. 61208
    Prev
    Next
    INDEX
    Explanations

    code identifiers

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

    This neuron activates on the opening single‐quote that begins a string literal 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_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
    '
    -2.48
     will
    -2.09
    6
    -1.73
    In
    -1.68
     essendo
    -1.66
    7
    -1.65
     five
    -1.63
    It
    -1.59
     fährt
    -1.53
     came
    -1.52
    POSITIVE LOGITS
     ellas
    1.88
    êmio
    1.85
     baseado
    1.81
    튿
    1.75
    蛲
    1.73
     quí
    1.71
    ⻬
    1.70
    荸
    1.66
     anoche
    1.63
     originalmente
    1.62
    Activations Density 0.022%

    No Known Activations