© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7403
    Prev
    Next
    INDEX
    Explanations

    followed by a list or details

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    When
    -1.57
     används
    -1.52
    Because
    -1.50
    графії
    -1.45
    地区
    -1.37
     apabila
    -1.36
    Whether
    -1.32
     because
    -1.30
    Whenever
    -1.30
     elseif
    -1.29
    POSITIVE LOGITS
    :
    2.27
     których
    1.59
     that
    1.51
     الذين
    1.39
     arasında
    1.29
     közül
    1.29
     którzy
    1.28
    <bos>
    1.24
     including
    1.23
     wichtigsten
    1.23
    Activations Density 0.068%

    No Known Activations