© 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. 16578
    Prev
    Next
    INDEX
    Explanations

    BY

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

    The neuron is primarily detecting standalone numeric tokens—especially multi‐digit page, line, or section numbers—in the document.

    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
     when
    -1.55
     example
    -1.44
     but
    -1.38
     there
    -1.32
     each
    -1.31
     several
    -1.24
     mentioned
    -1.21
     discussed
    -1.21
     during
    -1.20
     those
    -1.19
    POSITIVE LOGITS
     sisält
    1.12
    वरण
    1.05
     imprimé
    1.04
    OGUE
    1.02
     nawet
    1.02
    鸨
    1.02
    Année
    1.01
    Gründe
    1.00
    ykjav
    0.98
     TAMBÉM
    0.98
    Activations Density 0.343%

    No Known Activations