© 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. 64315
    Prev
    Next
    INDEX
    Explanations

    class definitions and code structures

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

    The neuron specializes in spotting numeric tokens (digit sequences or number literals) in code or 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
     fotográfico
    -1.07
     izquierdo
    -1.01
     așa
    -1.00
    
    -0.94
     renuncia
    -0.94
     ит
    -0.94
    的一些
    -0.94
    ְ
    -0.94
     obdob
    -0.93
     Erstellung
    -0.93
    POSITIVE LOGITS
     actually
    1.20
     actual
    1.13
     indeb
    0.96
     papir
    0.92
     bricola
    0.91
     bluza
    0.90
     spada
    0.90
     primit
    0.90
     poliester
    0.89
     kule
    0.88
    Activations Density 0.024%

    No Known Activations