© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119943
    Prev
    Next
    INDEX
    Explanations

    genes or protein subunits

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

    The neuron primarily detects letters within parentheses, particularly the letter "A" followed by a closing parenthesis.

    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
     there
    -1.92
    in
    -1.67
     your
    -1.59
    go
    -1.55
    between
    -1.54
    your
    -1.50
    you
    -1.48
    ations
    -1.46
     messaggi
    -1.45
    even
    -1.43
    POSITIVE LOGITS
    Vidéo
    1.56
     riuscito
    1.52
    Matériel
    1.45
    Toujours
    1.42
    Détails
    1.39
    Toute
    1.37
     Francus
    1.36
    Trong
    1.36
     olika
    1.34
    近日
    1.30
    Activations Density 0.031%

    No Known Activations