© 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. 127691
    Prev
    Next
    INDEX
    Explanations

    This neuron appears effectively inactive and does not reliably detect any particular pattern or tokens.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    Product details math and physics notation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ⊑
    -0.96
     adicionales
    -0.94
    Série
    -0.94
     lahko
    -0.94
    küche
    -0.88
    ෘ
    -0.87
    خخ
    -0.86
     contrari
    -0.86
    Перевод
    -0.86
    quartered
    -0.85
    POSITIVE LOGITS
     our
    1.16
     erzeugen
    1.05
     अन्य
    0.93
     a
    0.93
    当初
    0.92
     erzeugt
    0.90
    डा
    0.89
     bleiben
    0.88
     erzielt
    0.87
    ӗ
    0.87
    Activations Density 0.012%

    No Known Activations