© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30771
    Prev
    Next
    INDEX
    Explanations

    bus transactions

    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
    estimm
    -0.86
    Zapraszamy
    -0.76
    Dzięki
    -0.76
    éia
    -0.74
    ıştı
    -0.73
    britanni
    -0.72
    Dział
    -0.72
    Czas
    -0.70
    Uwaga
    -0.70
    tiske
    -0.70
    POSITIVE LOGITS
     transactions
    1.17
     bus
    1.10
     transaction
    0.98
    transactions
    0.96
     arbitration
    0.91
    bus
    0.87
    grant
    0.87
    GRANT
    0.85
     masters
    0.85
    masters
    0.84
    Activations Density 0.026%

    No Known Activations