© 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. 10-GEMMASCOPE-RES-131K
    7. 12395
    Prev
    Next
    INDEX
    Explanations

    exfoli, cortico, corpor

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

    terms related to chemical compounds and biological structures, particularly focusing on medical and scientific terminology.

    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
    1
    -3.11
     lauded
    -2.95
     alcuni
    -2.92
     wonderfully
    -2.92
     alcune
    -2.86
    2
    -2.83
     exceptionally
    -2.77
     Brings
    -2.69
    すでに
    -2.67
     largely
    -2.66
    POSITIVE LOGITS
    ?”
    2.86
    Ᏺ
    2.78
    طفال
    2.70
    "));
    2.67
    Ꮨ
    2.63
     ilustraciones
    2.56
    </h3>
    2.55
    )?
    2.52
    ”?
    2.47
    は
    2.47
    Activations Density 0.016%

    No Known Activations