© 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. 72559
    Prev
    Next
    INDEX
    Explanations

    following @ symbol

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

    This neuron fires on the “@” symbol used for annotations or decorator-style markers.

    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
    -3.45
    what
    -2.77
     If
    -2.67
    how
    -2.53
    and
    -2.52
     AND
    -2.42
     Saying
    -2.42
     Surely
    -2.42
     Some
    -2.41
    ників
    -2.39
    POSITIVE LOGITS
    ↵
    4.16
    寕
    3.09
    鬟
    2.72
    屨
    2.70
    閦
    2.70
    ᠁
    2.69
     ‐
    2.64
     夜景
    2.53
    '
    2.52
    
    2.52
    Activations Density 0.119%

    No Known Activations