© 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. 68959
    Prev
    Next
    INDEX
    Explanations

    clinical practice

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

    phrases related to clinical practice or medical/healthcare settings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects high-frequency, domain-specific two-word adjective–noun collocations (e.g. “clinical practice,” “technologically useful”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     alcune
    -1.30
    瞟
    -1.28
    ÉE
    -1.27
    zema
    -1.23
     into
    -1.23
    ᨆ
    -1.23
    owulf
    -1.22
     às
    -1.21
     the
    -1.20
    TRIBUTION
    -1.20
    POSITIVE LOGITS
    </u>
    1.37
     tych
    1.31
     these
    1.30
    </em>
    1.30
     situations
    1.28
    </h3>
    1.27
    <em>
    1.24
     adesi
    1.23
    </strong>
    1.22
    Antes
    1.21
    Activations Density 0.401%

    No Known Activations