© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 131002
    Prev
    Next
    INDEX
    Explanations

    demyelination, myelin, amyloid, sclerosis

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

    terminology related to myelin and demyelination in neurological contexts.

    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
    en
    -2.83
    t
    -2.61
    er
    -2.53
    把他
    -2.42
    if
    -2.31
    <i>
    -2.27
    es
    -2.27
    U
    -2.23
    al
    -2.23
    V
    -2.20
    POSITIVE LOGITS
    𓍊
    2.45
     啦
    1.89
    íamos
    1.87
    ሷ
    1.85
    ᯾
    1.85
     '
    1.84
    哙
    1.82
    錵
    1.82
    笄
    1.80
    。　　
    1.78
    Activations Density 0.060%

    No Known Activations