© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123691
    Prev
    Next
    INDEX
    Explanations

    biological interest

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

    scientific terminology in academic or technical texts.

    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
    遑
    -1.30
    觊
    -1.27
    ization
    -1.23
     justifyContent
    -1.23
    today
    -1.21
     '-';
    -1.20
    .
    -1.18
     Fully
    -1.16
    ijoje
    -1.16
    you
    -1.15
    POSITIVE LOGITS
     blatantly
    1.34
     schreef
    1.27
     нього
    1.23
    Bahan
    1.23
    ůměr
    1.23
    她说
    1.22
     profoundly
    1.20
    Educación
    1.20
    Harga
    1.20
     outright
    1.20
    Activations Density 0.261%

    No Known Activations