© 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. 70531
    Prev
    Next
    INDEX
    Explanations

    parentheses or slashes

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

    This neuron fires on numeric literals (integers or decimals) in code or markup.

    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
     его
    -0.92
    龱
    -0.90
     Estre
    -0.90
    怎麼辦
    -0.86
     Bajos
    -0.85
     Accesorios
    -0.84
    ”),
    -0.84
    fficacy
    -0.83
    parer
    -0.82
    romeda
    -0.82
    POSITIVE LOGITS
     also
    0.82
     divertida
    0.78
    isLogin
    0.76
     intricacies
    0.75
     sometimes
    0.73
     resulted
    0.71
     حتما
    0.70
     Thin
    0.70
     户
    0.69
     like
    0.69
    Activations Density 0.037%

    No Known Activations