© 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. 91546
    Prev
    Next
    INDEX
    Explanations

    medical scopes

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

    medical examination instruments and procedures related to endoscopy and visualization.

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

    This neuron detects mentions of medical inspection tools—words containing “scope” or “scopy” (e.g., endoscope, bronchoscopy, capsule endoscopy).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     упаков
    -0.74
    ޫ
    -0.72
    栽
    -0.69
    ዝ
    -0.66
     Onder
    -0.65
     Jaws
    -0.65
     xám
    -0.65
     Contractors
    -0.65
     Eno
    -0.65
    レン
    -0.64
    POSITIVE LOGITS
    scope
    1.38
     scope
    1.32
     oscilloscope
    1.13
     scopes
    1.13
    oscope
    1.11
    Scope
    1.10
    iscope
    1.07
    scoped
    1.05
    Scopes
    1.04
     Scope
    1.03
    Activations Density 0.057%

    No Known Activations