© 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. 34-GEMMASCOPE-RES-131K
    7. 55815
    Prev
    Next
    INDEX
    Explanations

    throat and airway conditions

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

    anatomical terms related to the throat and pharynx.

    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
     antenn
    -0.78
     telo
    -0.77
    hide
    -0.77
    ┛
    -0.76
     форм
    -0.74
     пору
    -0.73
     toile
    -0.73
     Showers
    -0.73
     femur
    -0.73
    glVertex
    -0.72
    POSITIVE LOGITS
     throat
    3.31
     throats
    2.69
     Throat
    2.33
    throat
    2.28
    Thro
    2.14
    喉
    1.91
     garganta
    1.80
     THRO
    1.60
     choking
    1.52
    throated
    1.42
    Activations Density 0.056%

    No Known Activations