© 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. 102112
    Prev
    Next
    INDEX
    Explanations

    chronic, acute, conditions

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

    The neuron activates for the word "chronic" and variations of "acute", with the highest activation specifically for "chronic" in medical and health contexts.

    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
    </i>
    -2.30
    窳
    -2.06
     téc
    -2.03
     แต่
    -1.99
     decidedly
    -1.95
    僦
    -1.91
     Our
    -1.89
     rác
    -1.88
     表情
    -1.85
    谖
    -1.84
    POSITIVE LOGITS
    Even
    2.31
    the
    2.30
    7
    2.27
    Not
    2.23
    Only
    2.17
    3
    2.11
    s
    2.11
    0
    2.09
    4
    2.09
    new
    2.08
    Activations Density 0.014%

    No Known Activations