© 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. 22-GEMMASCOPE-RES-131K
    7. 33709
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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_22/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
    yesterday
    -0.99
     domani
    -0.98
     istruzioni
    -0.97
     GmbH
    -0.96
     sabía
    -0.94
     selaku
    -0.90
    状態で
    -0.90
     mismos
    -0.89
    Yesterday
    -0.88
     bedrijf
    -0.88
    POSITIVE LOGITS
     then
    1.35
    チール
    0.98
     nemesis
    0.95
    Distribuzione
    0.90
    seling
    0.89
     because
    0.88
    があるので
    0.88
     включая
    0.88
    كامل
    0.87
    ֺ
    0.87
    Activations Density 0.013%

    No Known Activations