© 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. 22-GEMMASCOPE-RES-131K
    7. 65954
    Prev
    Next
    INDEX
    Explanations

    clinical trial, study, herb, shrub

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

    scientific study types, particularly "randomized controlled trial" and "cohort study" terms.

    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_22/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
    N
    -1.57
    J
    -1.46
    T
    -1.45
    B
    -1.39
    Z
    -1.36
    L
    -1.35
    M
    -1.34
    D
    -1.30
    G
    -1.30
    C
    -1.28
    POSITIVE LOGITS
     with
    1.68
     行っ
    1.49
    Rumah
    1.34
    Scooby
    1.27
    Lá
    1.27
     بیماری
    1.26
     kemer
    1.24
     utilisez
    1.23
    Waga
    1.23
    Tá
    1.22
    Activations Density 0.102%

    No Known Activations