© 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. 22-GEMMASCOPE-RES-131K
    7. 25037
    Prev
    Next
    INDEX
    Explanations

    ending quotes and punctuation in code

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

    This neuron fires on programming‐style tokens—especially import paths, module names, and other code identifiers—marking spans of source code rather than natural‐language text.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    It
    -1.26
     after
    -1.23
     when
    -1.16
     to
    -1.15
     that
    -1.10
     only
    -1.08
    There
    -1.04
     In
    -1.03
    The
    -1.02
     also
    -1.02
    POSITIVE LOGITS
     první
    1.19
     первом
    1.16
     coser
    1.14
     eerste
    1.13
    depuis
    1.01
     circons
    1.00
    fahrzeug
    0.99
    יפור
    0.97
    tisgarh
    0.96
    Redaktion
    0.96
    Activations Density 0.033%

    No Known Activations