© 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. 99751
    Prev
    Next
    INDEX
    Explanations

    health service appointments

    np_acts-logits-general · gemini-2.5-flash-lite

    locations and times of scheduled events or services.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    修炼
    -0.79
    phans
    -0.77
     fichiers
    -0.76
    bench
    -0.75
    的研究
    -0.73
    Bench
    -0.72
     bench
    -0.71
     policy
    -0.70
     Bench
    -0.70
    policy
    -0.69
    POSITIVE LOGITS
     clinic
    1.59
     clinics
    1.45
     appointment
    1.35
     sites
    1.32
     appointments
    1.30
    appointment
    1.27
     APPOINT
    1.24
    Appointments
    1.21
     site
    1.17
    Appointment
    1.17
    Activations Density 0.016%

    No Known Activations