© 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. 10-GEMMASCOPE-RES-131K
    7. 67569
    Prev
    Next
    INDEX
    Explanations

    hand hygiene

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

    words and phrases related to hand hygiene, washing, and sanitization.

    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_10/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
    -
    -1.88
     is
    -1.56
    i
    -1.52
    )
    -1.47
    ).
    -1.44
    l
    -1.44
     herida
    -1.41
     would
    -1.40
     whom
    -1.34
    ]
    -1.34
    POSITIVE LOGITS
    ཫ
    1.95
    isait
    1.63
    ISIONS
    1.60
    alties
    1.51
    Преимущества
    1.42
    bildning
    1.42
    🔖
    1.39
     потім
    1.38
     parachoque
    1.38
     impon
    1.38
    Activations Density 0.007%

    No Known Activations