© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70043
    Prev
    Next
    INDEX
    Explanations

    code keywords

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

    The neuron predominantly activates on numeric literals (numbers) 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
     it
    -1.72
    It
    -1.64
    1
    -1.46
    2
    -1.45
    ”،
    -1.45
    。《
    -1.41
    vierten
    -1.38
    Some
    -1.35
    There
    -1.34
    他們
    -1.31
    POSITIVE LOGITS
     jedna
    1.54
     otros
    1.41
     tämä
    1.41
     pól
    1.29
    TResult
    1.27
     yksi
    1.25
     این
    1.24
    IANT
    1.24
     jednej
    1.21
     Otros
    1.20
    Activations Density 0.059%

    No Known Activations