© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129464
    Prev
    Next
    INDEX
    Explanations

    taxonomic citations with author and year

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

    scientific names of authors in taxonomic citations with a surname followed by a publication year in parentheses.

    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_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
     which
    -1.03
    asinya
    -0.96
    бия
    -0.93
     انواع
    -0.93
    ですから
    -0.89
     cedera
    -0.88
    之际
    -0.87
    ViewChild
    -0.86
    Их
    -0.86
    álat
    -0.84
    POSITIVE LOGITS
     generaciones
    1.02
     vlasy
    1.00
     viena
    0.98
    wahati
    0.97
     требуется
    0.96
     निम्नलिखित
    0.96
    ických
    0.94
     antiguos
    0.94
    joni
    0.94
    ENIA
    0.94
    Activations Density 0.011%

    No Known Activations