© 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. 34-GEMMASCOPE-RES-131K
    7. 32963
    Prev
    Next
    INDEX
    Explanations

    scientific publications and studies

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

    numeric citations and references in scientific papers.

    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_34/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
    -0.98
     Every
    -0.94
    Every
    -0.93
     there
    -0.93
     every
    -0.93
     EVERY
    -0.93
     правительства
    -0.89
     spelar
    -0.88
    There
    -0.87
    People
    -0.87
    POSITIVE LOGITS
     strikingly
    0.89
     manuscript
    0.89
     stunning
    0.89
    साय
    0.88
     shimmering
    0.84
    Materials
    0.84
     manuscripts
    0.83
     publications
    0.83
     Kinh
    0.83
    ücks
    0.82
    Activations Density 0.035%

    No Known Activations