© 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. 64403
    Prev
    Next
    INDEX
    Explanations

    spatial traversal

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

    The neuron activates on multi‐digit numeric tokens (e.g. years, measurements, distances).

    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
     you
    -1.66
    ↵
    -1.62
    r
    -1.56
     which
    -1.46
    d
    -1.43
    .
    -1.43
     when
    -1.42
    a
    -1.40
    h
    -1.40
    ↵↵
    -1.39
    POSITIVE LOGITS
     the
    2.47
     camiset
    1.63
     mauva
    1.63
     vernis
    1.57
     纹身
    1.53
     ſont
    1.53
     trouvent
    1.52
    richtig
    1.48
     phénom
    1.48
     rámci
    1.47
    Activations Density 0.031%

    No Known Activations