© 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. 87316
    Prev
    Next
    INDEX
    Explanations

    lumbar spine medical conditions

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

    the anatomical term "lumbar" related to the lower spine in medical 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
     '
    -2.47
    /
    -2.41
    ."
    -2.30
     возле
    -2.30
     That
    -2.28
    Ꮏ
    -2.23
     ``
    -2.23
     sorprend
    -2.08
    на
    -2.00
    蕺
    -1.99
    POSITIVE LOGITS
    ⾳
    3.14
    ’,
    3.13
    鲠
    2.89
    峮
    2.89
    ,’
    2.86
     ส์
    2.86
    轳
    2.69
     лучших
    2.69
    噚
    2.69
    which
    2.63
    Activations Density 0.003%

    No Known Activations