© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7608
    Prev
    Next
    INDEX
    Explanations

    Yemen, diseases, oil, pages

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

    capitalized words or first words in lines of poetry, prayers, or religious 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
     or
    -1.76
     although
    -1.59
     but
    -1.56
     (
    -1.55
    </strong>
    -1.47
    There
    -1.44
     what
    -1.41
     of
    -1.36
     also
    -1.34
     there
    -1.27
    POSITIVE LOGITS
    ícias
    1.41
    																											
    1.34
     เป็น
    1.30
     Архивная
    1.27
    陡
    1.24
    onego
    1.23
     perfecte
    1.23
     keuntungan
    1.20
    eine
    1.18
     trei
    1.18
    Activations Density 0.020%

    No Known Activations