© 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. 22-GEMMASCOPE-RES-131K
    7. 93292
    Prev
    Next
    INDEX
    Explanations

    symptoms of

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

    The neuron activates strongly for the word "symptoms" in medical and health-related 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_22/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
     "
    -2.89
    ."
    -2.72
     ripping
    -2.31
    もの
    -2.20
    chyma
    -2.13
    轳
    -2.09
     但
    -2.05
    。
    -2.02
     '[
    -1.99
    of
    -1.96
    POSITIVE LOGITS
     cuch
    2.31
     namn
    2.25
    鱨
    2.13
    鮠
    2.03
    鈇
    2.03
     diffic
    2.02
    ’
    1.98
     valg
    1.98
     naam
    1.96
    蹕
    1.94
    Activations Density 0.019%

    No Known Activations