© 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. 7881
    Prev
    Next
    INDEX
    Explanations

    anniversary numbers and editions

    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
     by
    -1.55
     are
    -1.54
     to
    -1.52
     most
    -1.37
    <h2>
    -1.32
     conservazione
    -1.30
     compless
    -1.28
     algunas
    -1.25
     Američ
    -1.24
    those
    -1.23
    POSITIVE LOGITS
     guitare
    1.36
    henswürdigkeiten
    1.31
     tarta
    1.27
     chers
    1.23
    Модель
    1.22
    Цена
    1.20
     ados
    1.20
    　　“
    1.19
    Доба
    1.18
    درب
    1.18
    Activations Density 0.065%

    No Known Activations