© 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. 22-GEMMASCOPE-RES-131K
    7. 12494
    Prev
    Next
    INDEX
    Explanations

    medical, cultural, and linguistic topics

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

    punctuation marks (especially commas and periods) that appear at the end of sentences or phrases.

    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_22/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
    ！』
    -0.90
    ﾜ
    -0.80
     제공
    -0.79
    MEDIATE
    -0.79
    Vé
    -0.79
    Cpf
    -0.78
    굉
    -0.78
    páns
    -0.78
     musiciens
    -0.78
     in
    -0.78
    POSITIVE LOGITS
    owa
    1.03
    feliz
    1.03
     luxurious
    1.02
     ROCKS
    1.00
    ﾕ
    0.99
     безопасности
    0.94
    гиоз
    0.92
     DataAccess
    0.91
    腭
    0.91
     appre
    0.91
    Activations Density 0.225%

    No Known Activations