© 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. 63953
    Prev
    Next
    INDEX
    Explanations

    decoction

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

    The neuron detects words related to pharmaceutical or herbal preparations, particularly "decoction" and similar terms across different languages.

    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
     SKS
    -0.75
     megfe
    -0.73
     зустрі
    -0.73
     pingente
    -0.72
    вшийся
    -0.68
    Referencoj
    -0.67
    찾
    -0.66
     Yag
    -0.66
     bedtime
    -0.66
    Wra
    -0.66
    POSITIVE LOGITS
     util
    0.84
    itor
    0.81
     quanto
    0.81
     кре
    0.78
    IOR
    0.78
    sero
    0.77
     Nex
    0.77
    utz
    0.75
    mobile
    0.75
    éraires
    0.75
    Activations Density 0.034%

    No Known Activations