© 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. 64301
    Prev
    Next
    INDEX
    Explanations

    off

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

    The neuron is triggered by code punctuation (especially braces and semicolons) in programming-language snippets.

    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
     now
    -1.25
    PARE
    -1.20
    等は
    -1.10
    vají
    -1.09
     fundament
    -1.09
    ≦
    -1.07
    それでは
    -1.05
     gespe
    -1.04
     helle
    -1.04
     gerecht
    -1.03
    POSITIVE LOGITS
    ↵↵
    1.62
     which
    1.24
    0
    1.18
    」、
    1.07
     needed
    1.04
     bietet
    1.02
    ↵↵↵
    1.01
     kedua
    0.99
    無し
    0.99
    軻
    0.99
    Activations Density 0.007%

    No Known Activations