© 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. 71030
    Prev
    Next
    INDEX
    Explanations

    experiments carried out

    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
     would
    -1.70
     could
    -1.50
     having
    -1.44
     their
    -1.43
     should
    -1.38
     then
    -1.38
     being
    -1.35
    امي
    -1.35
     consequently
    -1.34
     focusing
    -1.34
    POSITIVE LOGITS
    翃
    1.59
    訁
    1.47
     geändert
    1.45
     également
    1.38
    ueling
    1.34
     opak
    1.31
    _",
    1.31
     сообщили
    1.28
     Zuhause
    1.28
     también
    1.28
    Activations Density 0.290%

    No Known Activations