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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91497
    Prev
    Next
    INDEX
    Explanations

    applications and uses

    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
     cornerback
    -1.02
     Bater
    -0.95
    iert
    -0.87
     potions
    -0.86
    thodoxy
    -0.85
    ندی
    -0.84
     Muerte
    -0.84
     FOTO
    -0.84
    اسي
    -0.83
    BlockingQueue
    -0.82
    POSITIVE LOGITS
     commercial
    2.19
     industrial
    1.87
     consumer
    1.77
     recreational
    1.73
    commercial
    1.58
     residential
    1.54
     civilian
    1.53
     military
    1.52
     leisure
    1.52
     agricultural
    1.52
    Activations Density 0.276%

    No Known Activations