© 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. 72391
    Prev
    Next
    INDEX
    Explanations

    spinal cord, fusion, anesthesia

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

    references to "spinal cord" in medical or neuroscience texts.

    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
    錞
    -2.80
    瀦
    -2.72
    xvii
    -2.56
     口罩
    -2.34
    
    -2.30
    hinh
    -2.22
    "",
    -2.22
    tano
    -2.17
    xvi
    -2.17
    '
    -2.16
    POSITIVE LOGITS
    re
    4.31
    u
    3.69
    a
    3.64
    an
    3.45
    e
    3.42
    isation
    3.27
    le
    2.97
    s
    2.92
    item
    2.91
    up
    2.75
    Activations Density 0.006%

    No Known Activations