© 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. 22-GEMMASCOPE-RES-131K
    7. 32594
    Prev
    Next
    INDEX
    Explanations

    various language terms

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

    The neuron activates on numeric measurements (i.e. numbers and numeric values) 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     you
    -2.27
     wouldn
    -1.55
     wasn
    -1.51
     isn
    -1.50
     didn
    -1.49
     I
    -1.46
     doesn
    -1.45
     You
    -1.39
     आपके
    -1.36
    harapkan
    -1.31
    POSITIVE LOGITS
     the
    1.66
     péché
    1.49
     TAMBÉM
    1.23
    PRAYER
    1.21
     agresión
    1.15
    tinggi
    1.14
     venit
    1.13
     we
    1.13
     such
    1.12
     ürün
    1.12
    Activations Density 0.117%

    No Known Activations