© 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. 64304
    Prev
    Next
    INDEX
    Explanations

    number and / or file extension

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

    The neuron is looking for numeric tokens or digit sequences (i.e. 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ↵↵
    -1.02
     have
    -1.02
     Bildschirm
    -0.94
     "
    -0.93
     Australia
    -0.91
     ebenso
    -0.90
    lüğü
    -0.87
    entance
    -0.86
    pdev
    -0.84
     проекти
    -0.84
    POSITIVE LOGITS
     őket
    1.33
    Tür
    1.13
    Grafik
    1.02
    谄
    1.02
    Leistungs
    1.02
    Hilfe
    1.00
     speel
    0.99
    Seiten
    0.99
    プリ
    0.98
    Texte
    0.97
    Activations Density 0.016%

    No Known Activations