© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38938
    Prev
    Next
    INDEX
    Explanations

    obstructive pulmonary disease

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

    words related to conditions or diseases, particularly respiratory and pulmonary conditions.

    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
    <td>
    -3.33
     antworte
    -3.16
    acterísticas
    -3.14
    י
    -3.05
    ⬯
    -2.69
    ي
    -2.67
    は
    -2.55
     falsche
    -2.52
     wußte
    -2.42
    其妙
    -2.38
    POSITIVE LOGITS
    a
    2.89
    𝄆
    2.88
    </h2>
    2.88
    
    2.86
    e
    2.75
    缡
    2.64
    灩
    2.59
    割と
    2.48
    甗
    2.45
    籏
    2.42
    Activations Density 0.035%

    No Known Activations