© 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. 71947
    Prev
    Next
    INDEX
    Explanations

    feeling happy, glad, or joyful

    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
    '
    -1.83
     a
    -1.65
     to
    -1.62
     <
    -1.58
    </strong>
    -1.58
    有不少
    -1.54
    enerbah
    -1.52
    irez
    -1.52
     soothe
    -1.51
     like
    -1.50
    POSITIVE LOGITS
    鹮
    1.92
     twa
    1.54
    оргаш
    1.52
     لر
    1.52
     wektor
    1.51
     gese
    1.50
     tornillos
    1.48
    犼
    1.48
    kese
    1.48
     excl
    1.47
    Activations Density 0.039%

    No Known Activations