© 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. 21865
    Prev
    Next
    INDEX
    Explanations

    errors and ailments

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

    words related to health problems, medical conditions, and technical issues.

    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
     the
    -1.84
     to
    -1.79
     for
    -1.78
     of
    -1.76
     mauva
    -1.48
     Californie
    -1.38
    💃
    -1.38
     kegiatan
    -1.36
    😜
    -1.35
    甶
    -1.35
    POSITIVE LOGITS
     preescolar
    1.47
    SqlDataReader
    1.38
     美しい
    1.30
     pierwszej
    1.30
    Aç
    1.28
    Kern
    1.28
    üstü
    1.28
    Alexa
    1.27
     パリ
    1.27
    Godzilla
    1.27
    Activations Density 0.462%

    No Known Activations