© 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. 1433
    Prev
    Next
    INDEX
    Explanations

    API documentation language medical code

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

    programming syntax elements like '#' symbols, code markers, and table names in various programming languages.

    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
    adalah
    -1.66
    daging
    -1.46
    ikti
    -1.45
    kritik
    -1.45
    </i>
    -1.45
     ujar
    -1.44
     компа
    -1.41
    ۷
    -1.40
    kannya
    -1.38
    здрав
    -1.36
    POSITIVE LOGITS
     how
    1.45
     рассказывает
    1.39
     отвечает
    1.37
    癭
    1.34
     registrada
    1.26
     получила
    1.20
     what
    1.17
     первого
    1.16
     sjø
    1.15
     имел
    1.15
    Activations Density 0.328%

    No Known Activations