© 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. 16711
    Prev
    Next
    INDEX
    Explanations

    plug housing, triplet, label, cleanUp, self-evaluation

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

    The neuron activates on numeric tokens (e.g. digits, measurements, version numbers, IP-like strings) 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    expl
    -0.89
    Beij
    -0.88
    tatuajes
    -0.85
     многих
    -0.85
    様です
    -0.84
     composição
    -0.82
    んだり
    -0.82
     blazing
    -0.82
     kobieta
    -0.81
     mivel
    -0.80
    POSITIVE LOGITS
     their
    0.88
    ángulo
    0.86
    width
    0.83
     sahaja
    0.83
    概要
    0.82
    RunAsync
    0.81
     prêmio
    0.79
    hkan
    0.78
    треть
    0.77
    ::::::::
    0.77
    Activations Density 0.040%

    No Known Activations