© 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. 34-GEMMASCOPE-RES-131K
    7. 79549
    Prev
    Next
    INDEX
    Explanations

    called or described by

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    keln
    -0.94
     показать
    -0.85
    Legende
    -0.84
     タワー
    -0.84
     zeigen
    -0.84
    çeği
    -0.84
     zeigt
    -0.83
     menunjukkan
    -0.82
    shown
    -0.82
    INCREMENT
    -0.81
    POSITIVE LOGITS
     called
    4.66
     calling
    3.94
     call
    3.80
     calls
    3.47
     gọi
    3.17
    called
    3.11
    Calling
    3.08
    Called
    3.05
     Calling
    2.92
     Called
    2.89
    Activations Density 0.092%

    No Known Activations