© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 837
    Prev
    Next
    INDEX
    Explanations

    name and surname

    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
    ITCHEN
    -1.64
     werd
    -1.63
     volumen
    -1.59
    {
    -1.55
    рино
    -1.52
    -1.52
    setdefault
    -1.51
     los
    -1.50
    $};
    -1.50
    {
    -1.48
    POSITIVE LOGITS
    푣
    2.00
     therefore
    1.92
     ongeveer
    1.77
    栱
    1.77
    ترت
    1.77
    ¹,
    1.76
     who
    1.75
     Люди
    1.69
    s
    1.64
     można
    1.62
    Activations Density 0.018%

    No Known Activations