© 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. 10-GEMMASCOPE-RES-131K
    4. 1190
    Prev
    Next
    INDEX
    Explanations

    hep-ph and hepatitis

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

    scientific abbreviations like "hep" and scientific paper identifiers.

    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
     then
    -2.31
    一旁
    -2.23
     but
    -2.22
     to
    -2.19
     that
    -2.06
     which
    -2.05
    '
    -1.82
     know
    -1.76
     as
    -1.75
    的吧
    -1.74
    POSITIVE LOGITS
    </strong>
    2.98
     ſta
    2.19
     ";
    
    2.06
    при
    1.98
    簓
    1.94
    tttt
    1.88
     faſt
    1.88
    Если
    1.86
    для
    1.83
    蟳
    1.80
    Activations Density 0.003%

    No Known Activations