© 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. 34-GEMMASCOPE-RES-131K
    4. 53937
    Prev
    Next
    INDEX
    Explanations

    scientific reviews

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

    citation numbers in academic papers, particularly in parenthetical references.

    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
     if
    -0.95
     so
    -0.90
     which
    -0.88
     on
    -0.87
    meldet
    -0.85
    ņem
    -0.85
     impeccable
    -0.85
    un
    -0.83
    JHEP
    -0.83
     Greenhouse
    -0.82
    POSITIVE LOGITS
     review
    2.58
     reviews
    2.31
     reviewing
    1.99
     Review
    1.95
    review
    1.94
    reviews
    1.84
    Review
    1.83
     overview
    1.79
     Reviews
    1.77
     reviewed
    1.77
    Activations Density 0.027%

    No Known Activations