© 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. 58179
    Prev
    Next
    INDEX
    Explanations

    links and urls

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

    This neuron primarily responds to standalone numeric tokens (e.g. vote counts or other numbers, including decimals).

    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
     you
    -1.59
     casado
    -1.34
    是一款
    -1.27
    AllAfrica
    -1.24
    anız
    -1.24
     questo
    -1.23
     hendes
    -1.23
    tualmente
    -1.21
     iar
    -1.19
    앵
    -1.19
    POSITIVE LOGITS
    those
    1.29
    raisers
    1.28
    fillment
    1.28
    entown
    1.26
    tician
    1.26
    cznego
    1.23
    実に
    1.23
    ulitis
    1.23
     Thankfully
    1.23
     even
    1.20
    Activations Density 0.023%

    No Known Activations