© 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. 113393
    Prev
    Next
    INDEX
    Explanations

    election primaries

    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
    “
    -2.47
    </h3>
    -2.39
    {
    -2.34
    .
    -2.03
    >
    -2.00
    !
    -1.96
     However
    -1.84
    </em>
    -1.78
     SHOULD
    -1.73
    de
    -1.71
    POSITIVE LOGITS
     sonriendo
    2.05
    ܜ
    2.03
     sonriente
    1.83
    笵
    1.83
    ization
    1.82
     llorando
    1.77
    嚅
    1.77
     chère
    1.69
     ยาว
    1.61
     叶子
    1.59
    Activations Density 0.007%

    No Known Activations