© 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. 22572
    Prev
    Next
    INDEX
    Explanations

    start of code or questions

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

    The neuron activates strongly on numeric tokens—especially floating‐point numbers and version‐style decimals.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     этой
    -1.79
    ==""){
    -1.71
     sostenible
    -1.68
     gastronomía
    -1.65
     dvě
    -1.63
     propietarios
    -1.60
     maceta
    -1.59
     artesanía
    -1.58
    erweise
    -1.55
    ciri
    -1.55
    POSITIVE LOGITS
    Those
    1.89
     Those
    1.84
     semasa
    1.81
     While
    1.80
     trattano
    1.73
     but
    1.73
    ној
    1.73
    Although
    1.70
     However
    1.69
     Depending
    1.68
    Activations Density 0.000%

    No Known Activations