© 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. 58857
    Prev
    Next
    INDEX
    Explanations

    therapy involving suction and pressure

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

    medical and therapeutic devices, particularly those involving electrical stimulation or pressure applications.

    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
     Feeds
    -0.78
    堝
    -0.73
     Indians
    -0.72
    激光
    -0.71
    Feeds
    -0.71
     LASER
    -0.71
     Lasers
    -0.68
     sugary
    -0.68
    bastian
    -0.67
    ngày
    -0.67
    POSITIVE LOGITS
    therapy
    0.96
    gorithm
    0.92
     piston
    0.83
    flutter
    0.81
     therapy
    0.81
    Rental
    0.80
     mieszkańców
    0.78
     THERAPY
    0.78
     Cups
    0.77
    owy
    0.77
    Activations Density 0.021%

    No Known Activations