© 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. 10-GEMMASCOPE-RES-131K
    7. 6725
    Prev
    Next
    INDEX
    Explanations

    foreign or technical words

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

    This neuron detects numeric literal tokens (i.e. numbers) in the text.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    N
    -1.98
    are
    -1.70
    is
    -1.66
    centerTitle
    -1.64
    今年
    -1.64
    M
    -1.63
    al
    -1.62
     dreaded
    -1.59
    than
    -1.58
    昨天
    -1.56
    POSITIVE LOGITS
     which
    1.76
     when
    1.73
     Bedürfn
    1.70
     ausdrück
    1.59
     murieron
    1.55
     because
    1.54
     and
    1.54
     één
    1.53
     but
    1.52
    饪
    1.52
    Activations Density 0.012%

    No Known Activations