© 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. 1516
    Prev
    Next
    INDEX
    Explanations

    hemodynamic monitoring and therapy

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

    The neuron detects words and concepts related to educational and academic contexts, particularly learning systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires most on longer, content‐bearing (often technical or less common) words rather than short function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     to
    -1.95
     in
    -1.80
    gencias
    -1.47
    」
    -1.38
    {
    -1.33
     bardziej
    -1.27
     again
    -1.27
    vedades
    -1.27
    ";
    -1.24
    ')"
    -1.24
    POSITIVE LOGITS
    lahir
    1.49
    
    1.43
     baskılı
    1.43
    Typically
    1.42
    carnated
    1.41
    ⍽
    1.41
    věř
    1.39
    ֹא
    1.39
    řad
    1.36
    accord
    1.33
    Activations Density 0.062%

    No Known Activations