© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67696
    Prev
    Next
    INDEX
    Explanations

    writing contests and code

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

    The neuron detects occurrences of the double‐pipe operator “||” 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
    鸶
    -2.78
     \
    -2.67
    नलोड
    -2.66
     новая
    -2.58
    ндарт
    -2.53
    𝝈
    -2.48
    pecabe
    -2.45
    觏
    -2.41
    ᯾
    -2.39
     Its
    -2.38
    POSITIVE LOGITS
    '
    2.84
    Having
    2.81
    What
    2.58
    Our
    2.56
    From
    2.52
    Like
    2.50
    Considering
    2.48
    With
    2.47
    ”,
    2.45
    
    2.45
    Activations Density 0.001%

    No Known Activations