© 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. 34-GEMMASCOPE-RES-131K
    7. 102983
    Prev
    Next
    INDEX
    Explanations

    MEDLINE category terms

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

    legal document formatting elements including case names, citations, and category headers.

    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
    сё
    -0.90
    Их
    -0.89
    シェフ
    -0.89
    はいけない
    -0.83
     THE
    -0.80
    (?:
    -0.80
    Схема
    -0.79
     partout
    -0.78
    Зачем
    -0.78
     zarówno
    -0.78
    POSITIVE LOGITS
    United
    1.02
     будущее
    0.91
     animals
    0.90
     conferencias
    0.88
     United
    0.88
     Velas
    0.88
     odors
    0.87
     buildings
    0.87
     Humanos
    0.86
     linked
    0.85
    Activations Density 0.068%

    No Known Activations