© 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. 90485
    Prev
    Next
    INDEX
    Explanations

    GRAND magazine, MEDLINE, BIOHAZARD, OUTLOOK

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

    capital letter text/headings at the beginning of documents.

    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
     without
    -1.67
     there
    -1.66
     takže
    -1.41
     on
    -1.36
     until
    -1.34
     before
    -1.32
     first
    -1.32
     noteworthy
    -1.28
     out
    -1.27
     started
    -1.27
    POSITIVE LOGITS
    筇
    1.58
    ほんとに
    1.56
     hırka
    1.48
     rése
    1.45
    obé
    1.45
    ladung
    1.41
     ۵
    1.40
    蚰
    1.39
    ػ
    1.37
     dévo
    1.32
    Activations Density 0.147%

    No Known Activations