© 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. 127278
    Prev
    Next
    INDEX
    Explanations

    tar sands, Kurs, start, disease, declines, children, limiting factor, list, darling

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

    topics or keywords in technical or scientific content.

    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
     you
    -1.63
     recientes
    -1.41
     be
    -1.36
     decoradas
    -1.36
    saurus
    -1.35
     marcadas
    -1.34
    Dichlor
    -1.20
     découvrez
    -1.19
    种类
    -1.17
    ⢫
    -1.16
    POSITIVE LOGITS
    thodoxy
    1.70
    ↵↵↵
    1.53
    iamo
    1.52
    therners
    1.44
     its
    1.36
    llllll
    1.31
    oys
    1.31
    much
    1.31
    是我的
    1.30
    cheme
    1.30
    Activations Density 0.209%

    No Known Activations