© 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. 80679
    Prev
    Next
    INDEX
    Explanations

    spleen and lymphocytes

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

    The neuron detects the word "spleen" and related terminology in medical or scientific texts.

    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
    翃
    -2.28
     These
    -2.20
     bustling
    -2.17
    ”;
    -2.16
     Tienen
    -2.06
    大半
    -2.02
     elevate
    -1.99
     Importantly
    -1.98
     Then
    -1.95
    onsense
    -1.95
    POSITIVE LOGITS
    isation
    2.00
     of
    1.95
    }
    1.92
     spleen
    1.92
     hadi
    1.87
    鱨
    1.85
    {
    1.85
    at
    1.84
     hata
    1.84
     contento
    1.83
    Activations Density 0.009%

    No Known Activations