© 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. 21077
    Prev
    Next
    INDEX
    Explanations

    happiness and joy

    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
    塒
    -3.39
    拊
    -3.13
    ￨
    -3.06
    猻
    -3.00
    푡
    -3.00
     MÉXICO
    -2.98
    塍
    -2.95
    啣
    -2.95
    玧
    -2.94
    诹
    -2.94
    POSITIVE LOGITS
    This
    3.69
    *
    3.56
    ]
    3.44
    {
    3.39
    While
    3.25
    There
    3.20
    3
    3.17
    2
    3.17
     There
    3.16
    .
    3.13
    Activations Density 0.002%

    No Known Activations