© 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. 67035
    Prev
    Next
    INDEX
    Explanations

    more on that later

    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
    ATIONS
    -1.62
     dinámico
    -1.50
     the
    -1.48
    atürk
    -1.34
     onlyOwner
    -1.34
     VIEW
    -1.34
    *
    -1.31
     JTextField
    -1.30
    <0xF1>
    -1.30
    əri
    -1.30
    POSITIVE LOGITS
    Пла
    1.55
    рами
    1.35
    Publica
    1.30
    Maintenant
    1.30
    Ngày
    1.26
    Deux
    1.20
    Тре
    1.20
    좋
    1.18
    We
    1.17
    我们的
    1.17
    Activations Density 0.026%

    No Known Activations