© 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. 34-GEMMASCOPE-RES-131K
    4. 65840
    Prev
    Next
    INDEX
    Explanations

    photodynamic therapy and lasers

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

    references to light-based therapies including lasers, LED, photodynamic therapy, and various light wavelengths.

    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
     perfume
    -0.87
     Substitute
    -0.82
     Mure
    -0.82
    inspiring
    -0.82
    پیوند
    -0.81
     Perfume
    -0.80
    ogram
    -0.77
     parag
    -0.76
    Parking
    -0.76
     CONNECT
    -0.75
    POSITIVE LOGITS
     therapy
    1.46
     treatment
    1.25
     device
    1.21
     frequencies
    1.20
     wavelength
    1.19
     frequency
    1.15
     devices
    1.15
     wavelengths
    1.09
     sessions
    1.07
     infrared
    1.07
    Activations Density 0.065%

    No Known Activations