© 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. 84624
    Prev
    Next
    INDEX
    Explanations

    active followed by classifications

    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
     corredor
    -1.77
    ні
    -1.73
     apoi
    -1.67
     suporta
    -1.65
    {
    -1.57
    lhes
    -1.55
    спи
    -1.52
    hhh
    -1.51
    кови
    -1.48
    кость
    -1.47
    POSITIVE LOGITS
    ?”
    1.81
    Even
    1.80
     можно
    1.74
    During
    1.71
    ?"
    1.70
    !”
    1.64
     был
    1.64
     deutscher
    1.61
    Although
    1.60
    Regardless
    1.60
    Activations Density 0.019%

    No Known Activations