© 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. 6807
    Prev
    Next
    INDEX
    Explanations

    common names

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

    The neuron activates on numeric tokens—especially table cell values and floating‐point numbers.

    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
     the
    -1.80
     our
    -1.70
     both
    -1.48
     laiton
    -1.31
    🚥
    -1.30
    adır
    -1.23
    деб
    -1.22
    فرش
    -1.15
    ässer
    -1.15
    То
    -1.14
    POSITIVE LOGITS
    ֶּ
    1.81
     düşük
    1.48
    ּוֹ
    1.44
     nė
    1.34
     to
    1.34
    着一个
    1.33
     nyky
    1.32
    casila
    1.30
    boîte
    1.27
     current
    1.24
    Activations Density 0.314%

    No Known Activations