© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40279
    Prev
    Next
    INDEX
    Explanations

    pragmatic clinical approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    皛
    -2.91
    噥
    -2.84
    泐
    -2.70
    氿
    -2.70
    蟜
    -2.67
    訁
    -2.67
    ครื่อง
    -2.66
    푢
    -2.61
    嗄
    -2.61
     profondità
    -2.58
    POSITIVE LOGITS
    H
    3.44
    R
    3.39
    U
    3.30
    F
    3.13
    *
    3.11
    J
    3.00
    E
    2.98
    C
    2.94
    M
    2.88
    T
    2.84
    Activations Density 0.003%

    No Known Activations