© 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. 83872
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and code delimiters

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

    The neuron activates on numeric tokens (including integers and decimals), i.e. it detects 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
     with
    -2.14
     during
    -1.66
     took
    -1.51
     sehr
    -1.51
     any
    -1.51
     began
    -1.48
     very
    -1.43
     first
    -1.42
     used
    -1.41
     During
    -1.41
    POSITIVE LOGITS
     konkret
    1.65
     planten
    1.58
     they
    1.57
     konkrete
    1.56
    ahh
    1.55
     Création
    1.54
     Agregar
    1.53
     werkt
    1.52
     konkrét
    1.50
     nimmer
    1.48
    Activations Density 0.001%

    No Known Activations