© 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. 77781
    Prev
    Next
    INDEX
    Explanations

    surfaces and sanitation

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

    content related to cleaning, sanitization, contamination, and surfaces.

    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
     Fanny
    -0.88
    теры
    -0.79
     stench
    -0.78
     tubeless
    -0.77
     Canna
    -0.77
    iltà
    -0.76
    绪
    -0.75
     partículas
    -0.74
    トラブル
    -0.73
    diferentes
    -0.73
    POSITIVE LOGITS
     surfaces
    2.67
     Surfaces
    1.93
    surfaces
    1.86
     surface
    1.73
     touch
    1.61
    Surface
    1.55
     touched
    1.52
     поверхности
    1.51
    surface
    1.48
     Oberflächen
    1.35
    Activations Density 0.010%

    No Known Activations