© 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. 21187
    Prev
    Next
    INDEX
    Explanations

    exceptional example condition

    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
     it
    -1.79
     to
    -1.74
    着一个
    -1.60
     harika
    -1.39
    DeclareMath
    -1.38
     tiež
    -1.35
     seleccione
    -1.34
     largely
    -1.30
     is
    -1.30
     também
    -1.29
    POSITIVE LOGITS
    私が
    1.42
     such
    1.30
     قدیمی
    1.23
    Affirmed
    1.21
    ambut
    1.20
    kopi
    1.20
    高温
    1.17
    diğimiz
    1.17
    UserScript
    1.17
     that
    1.16
    Activations Density 0.044%

    No Known Activations