© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90695
    Prev
    Next
    INDEX
    Explanations

    German, French, and Indian locations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     by
    -1.16
     even
    -1.06
     Even
    -1.02
     this
    -0.99
     various
    -0.98
     from
    -0.94
     also
    -0.93
     July
    -0.93
     Various
    -0.91
     for
    -0.88
    POSITIVE LOGITS
    rüstung
    1.07
    ↵↵
    1.05
    sprecher
    1.04
    ↵
    1.02
     Guadeloupe
    0.94
    geschlossen
    0.93
     INDIA
    0.93
    änderungen
    0.93
    wirkungen
    0.92
     Dulles
    0.92
    Activations Density 0.006%

    No Known Activations