© 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. 31283
    Prev
    Next
    INDEX
    Explanations

    sports injuries and medical conditions

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

    terms and phrases related to sports injuries and medical conditions.

    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
     Glau
    -0.87
     Stimulation
    -0.86
     ordin
    -0.81
    Tumor
    -0.79
    Passenger
    -0.79
     besø
    -0.79
     housekeeping
    -0.78
     uintptr
    -0.77
     Actu
    -0.76
     dentures
    -0.75
    POSITIVE LOGITS
     injury
    1.45
     injuries
    1.34
     Injury
    1.19
     elite
    1.17
     athletes
    1.17
     players
    1.14
     risk
    1.13
     injured
    1.10
     player
    1.09
     season
    1.08
    Activations Density 0.069%

    No Known Activations