© 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. 45487
    Prev
    Next
    INDEX
    Explanations

    strings containing code or special characters

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

    The neuron is keyed to the double‐quote character (i.e. it fires on the string delimiter `"`).

    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
     Saltar
    -1.80
     brinda
    -1.61
     Bücher
    -1.61
     elige
    -1.56
     encuentras
    -1.55
     sudadera
    -1.53
     proporciona
    -1.52
    是一位
    -1.51
     continúas
    -1.50
     podes
    -1.50
    POSITIVE LOGITS
     endeavoured
    1.90
    我们
    1.84
     geringen
    1.59
    WITH
    1.56
     meager
    1.55
     beliebtesten
    1.54
    yeron
    1.53
    omyces
    1.53
    EventListener
    1.52
    astify
    1.52
    Activations Density 0.007%

    No Known Activations