© 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. 62852
    Prev
    Next
    INDEX
    Explanations

    hyperbaric oxygen pressure

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

    medical and scientific terminology related to hyperbaric oxygen therapy and pressure 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_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
    cipit
    -0.71
    之际
    -0.70
    lan
    -0.70
    chon
    -0.66
     Cong
    -0.66
    minator
    -0.64
     Montagu
    -0.64
    packaging
    -0.64
     wä
    -0.63
     packaging
    -0.63
    POSITIVE LOGITS
     hyper
    1.78
    Hyper
    1.75
     Hyper
    1.66
    hyper
    1.63
     chamber
    1.49
     HYPER
    1.33
     hiper
    1.25
    chamber
    1.24
     HBO
    1.21
     Chamber
    1.19
    Activations Density 0.036%

    No Known Activations