© 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. 9334
    Prev
    Next
    INDEX
    Explanations

    specific word sequences

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

    The neuron fires on clinical and biomedical terms—especially disease names, diagnostic or treatment descriptors, and related condition 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_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
     esconder
    -1.05
    ᨆ
    -1.05
     restent
    -1.03
     aranha
    -1.02
    ～！
    -0.98
    
    -0.98
     pôr
    -0.98
    Huhu
    -0.97
    Componentes
    -0.97
    Aç
    -0.96
    POSITIVE LOGITS
     produziert
    1.13
     कथ
    1.05
    Q
    1.05
     verknüp
    1.00
     can
    0.97
     bestimmen
    0.94
    ќ
    0.93
    J
    0.92
     فى
    0.92
    //
    0.91
    Activations Density 0.066%

    No Known Activations