© 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. 64530
    Prev
    Next
    INDEX
    Explanations

    word or common prefix

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

    This neuron activates on the “%” symbol used to mark SPIR-V or similar intermediate-code identifiers.

    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
    Those
    -1.19
    
    -1.16
     in
    -1.13
     people
    -1.07
     Depending
    -1.04
    czerw
    -1.00
    *}[
    -0.99
     should
    -0.98
     to
    -0.98
     Those
    -0.98
    POSITIVE LOGITS
     such
    1.04
    并未
    1.03
     jakim
    1.00
     among
    0.99
     energías
    0.97
    .
    0.95
    aneo
    0.94
    ieniem
    0.94
    ix
    0.94
    uch
    0.90
    Activations Density 0.000%

    No Known Activations