© 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. 978
    Prev
    Next
    INDEX
    Explanations

    pneumococcal disease

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

    scientific or technical terms, particularly related to biology, medicine, and technology.

    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
    しないで
    -2.53
    E
    -2.41
    𐐪
    -2.39
     beginnings
    -2.39
    中国的
    -2.31
     kurzen
    -2.25
     persönlichen
    -2.23
    ه
    -2.20
    ありがとう
    -2.14
     schnellen
    -2.14
    POSITIVE LOGITS
    注意事
    3.28
     GOtt
    2.66
     dieß
    2.55
    sandalia
    2.53
    咴
    2.48
     auffi
    2.44
    ндарт
    2.39
    櫺
    2.34
    rufen
    2.34
    '.
    2.33
    Activations Density 0.015%

    No Known Activations