© 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. 10-GEMMASCOPE-RES-131K
    7. 103222
    Prev
    Next
    INDEX
    Explanations

    alveolar space structures

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

    medical and anatomical terms related to the alveoli in lungs or respiratory system.

    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
    ”)
    -2.20
     []),
    -1.78
    蠵
    -1.78
     mélanger
    -1.78
    わけではない
    -1.75
    </b>
    -1.74
     ブラウス
    -1.69
     ”
    -1.69
     appeler
    -1.68
    ”，
    -1.67
    POSITIVE LOGITS
    ."
    2.03
    )
    1.94
    </h3>
    1.93
    岽
    1.89
    双方
    1.88
     relentlessly
    1.85
    謳
    1.74
     ול
    1.73
     '
    1.70
     excessively
    1.66
    Activations Density 0.060%

    No Known Activations