© 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. 34-GEMMASCOPE-RES-131K
    7. 29989
    Prev
    Next
    INDEX
    Explanations

    code and names

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

    The neuron detects numeric tokens—i.e. sequences of digits.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    表彰
    -0.71
     kinerja
    -0.71
    asem
    -0.68
    ülle
    -0.67
    Artic
    -0.66
    pastebin
    -0.66
     electronic
    -0.65
     keys
    -0.65
     Zugang
    -0.65
    彰
    -0.65
    POSITIVE LOGITS
     Reiki
    0.76
    řed
    0.69
     Abad
    0.69
     IPM
    0.69
    Davies
    0.68
    Referencer
    0.68
     SUGGEST
    0.67
     übergeben
    0.66
     Davies
    0.65
    ۃ
    0.64
    Activations Density 0.081%

    No Known Activations