© 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. 22-GEMMASCOPE-RES-131K
    7. 14803
    Prev
    Next
    INDEX
    Explanations

    health care communication

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

    customer service and problem-resolution scenarios in text.

    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_22/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
     boto
    -1.08
     bara
    -1.07
     döner
    -0.96
    chnen
    -0.95
     Stadion
    -0.94
    tidae
    -0.93
     יִ
    -0.91
     abad
    -0.91
     hotell
    -0.90
     msglen
    -0.89
    POSITIVE LOGITS
     agency
    1.01
     різних
    0.97
     ofrecer
    0.93
     начинается
    0.91
     institutions
    0.91
     zufried
    0.88
     enmar
    0.88
     assistant
    0.88
     agencias
    0.87
     Geräte
    0.85
    Activations Density 0.088%

    No Known Activations