© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38509
    Prev
    Next
    INDEX
    Explanations

    documentation blocks with @ tags

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

    This neuron activates on the “@” symbol (e.g. in annotations or docblock tags).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    inheritDoc
    -2.31
    嶇
    -2.17
     mengucap
    -2.09
    ’,
    -2.08
    </u>
    -2.03
     anniversaire
    -1.99
     ähnliche
    -1.98
     ersten
    -1.98
     aktuellen
    -1.98
     років
    -1.95
    POSITIVE LOGITS
    sandalia
    2.25
    jaqueta
    2.23
    蒾
    2.16
    
    2.06
    '
    2.00
    涐
    1.99
    咵
    1.98
    璈
    1.94
    
    1.89
    
    1.84
    Activations Density 0.011%

    No Known Activations