© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66191
    Prev
    Next
    INDEX
    Explanations

    genetic diversity, discrete spacers

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

    page numbers in academic citations, particularly those with hyphenated ranges.

    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
     to
    -0.98
    ()}>
    -0.95
     несколь
    -0.95
    gey
    -0.85
    了自己的
    -0.84
     durante
    -0.83
     ليس
    -0.82
    だけではなく
    -0.82
     تمامی
    -0.82
    uzen
    -0.82
    POSITIVE LOGITS
     coincides
    0.86
     enhances
    0.86
    ืม
    0.85
    Etter
    0.85
     zajíma
    0.84
    Dolly
    0.82
    richlet
    0.81
     commanders
    0.81
    Mitä
    0.81
     orquí
    0.81
    Activations Density 0.003%

    No Known Activations