© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105380
    Prev
    Next
    INDEX
    Explanations

    physical and occupational therapy

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

    references to physical therapy and physiotherapy services or treatments.

    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_10/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
    -1.78
    i
    -1.49
     cuya
    -1.29
    思わず
    -1.20
    …
    -1.17
     не
    -1.16
    "
    -1.16
     سے
    -1.15
     —
    -1.15
     –
    -1.13
    POSITIVE LOGITS
    OCCURRED
    1.48
    moreland
    1.38
    OREM
    1.33
     sorella
    1.30
    ("${
    1.30
     trochu
    1.30
    CLUSIVE
    1.27
     ajutor
    1.27
    graphy
    1.27
     dichos
    1.27
    Activations Density 0.035%

    No Known Activations