© 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. 7782
    Prev
    Next
    INDEX
    Explanations

    power and loads

    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
     to
    -1.77
     particularmente
    -1.29
    ticularly
    -1.19
    XCTAssertEqual
    -1.14
     do
    -1.14
     or
    -1.11
    んびり
    -1.11
     particularly
    -1.08
     help
    -1.07
     especially
    -1.07
    POSITIVE LOGITS
     a
    1.54
    现在
    1.34
    ！！！”
    1.30
    因为
    1.21
    ！！”
    1.20
    مدیر
    1.18
     теперь
    1.17
     polega
    1.16
    ्रीय
    1.15
    在我们
    1.14
    Activations Density 0.214%

    No Known Activations