© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27711
    Prev
    Next
    INDEX
    Explanations

    xml tags and attributes

    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
     since
    -1.24
     would
    -1.22
     because
    -1.20
     this
    -1.05
     even
    -1.05
     from
    -1.05
     have
    -1.02
    WidgetItem
    -1.00
    MPA
    -0.96
     should
    -0.94
    POSITIVE LOGITS
    Diese
    1.13
     только
    1.07
     rác
    1.03
    Eine
    1.02
    Leider
    1.02
    ៛
    1.01
    Beim
    1.00
     بندی
    1.00
    Unsere
    1.00
    }\
    0.99
    Activations Density 0.001%

    No Known Activations