© 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. 16517
    Prev
    Next
    INDEX
    Explanations

    Q A code snippets

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

    The neuron activates on numeric literal tokens (multi‐digit numbers) in code or markup.

    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
     has
    -1.66
     that
    -1.63
     might
    -1.63
     will
    -1.51
     for
    -1.48
     may
    -1.42
     these
    -1.41
     appears
    -1.35
     seems
    -1.33
     should
    -1.30
    POSITIVE LOGITS
     symptômes
    1.44
     réinitial
    1.41
     STARTED
    1.38
    ebly
    1.35
     garant
    1.31
    놋
    1.30
     скриншот
    1.29
     CREATED
    1.28
    ichert
    1.27
    ⅙
    1.27
    Activations Density 0.000%

    No Known Activations