© 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. 34-GEMMASCOPE-RES-131K
    7. 64602
    Prev
    Next
    INDEX
    Explanations

    glands and their secretions

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

    anatomical structures related to glands and secretory organs in biological/medical text.

    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_34/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
     shadows
    -0.78
    زون
    -0.76
     roads
    -0.75
    Bubbles
    -0.73
     espace
    -0.73
    hems
    -0.72
     restre
    -0.72
     famille
    -0.72
     soul
    -0.71
     regarde
    -0.71
    POSITIVE LOGITS
     glands
    1.93
     gland
    1.30
    腺
    1.02
     salivary
    0.99
     sweat
    0.97
    Modification
    0.88
     paired
    0.88
     Brunner
    0.87
    Oil
    0.86
     Gland
    0.84
    Activations Density 0.097%

    No Known Activations