© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1437
    Prev
    Next
    INDEX
    Explanations

    morphology and pathology

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

    The neuron activates for the word "morphology" and related terms describing physical structure or appearance of organisms, cells, or materials.

    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
    ?"
    -3.08
    !"
    -2.83
    utched
    -2.64
    好吃的
    -2.59
     criticised
    -2.56
    齜
    -2.44
    '
    -2.39
    を
    -2.39
    </i>
    -2.38
    瞜
    -2.38
    POSITIVE LOGITS
    .
    3.41
    </h4>
    2.67
    ↵↵
    2.59
    </sup>
    2.41
     of
    2.34
     geringen
    2.34
    ?
    2.22
    e
    2.19
     серебри
    2.16
     Ergänzung
    2.16
    Activations Density 0.078%

    No Known Activations