© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82297
    Prev
    Next
    INDEX
    Explanations

    body part injuries

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

    references to injuries, particularly knee injuries, in sports reporting.

    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
    IDENCE
    -0.93
     AudioClip
    -0.90
     akibat
    -0.80
    енных
    -0.79
    Tris
    -0.78
    пада
    -0.75
    போ
    -0.74
     turban
    -0.73
    レオ
    -0.73
     Reunion
    -0.73
    POSITIVE LOGITS
     issue
    1.58
     issues
    1.45
     injury
    1.30
     problem
    1.29
     problems
    1.11
     problémy
    1.11
     trouble
    1.07
     problemas
    1.07
     troubles
    1.04
    issue
    1.03
    Activations Density 0.017%

    No Known Activations