© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86034
    Prev
    Next
    INDEX
    Explanations

    honorifics and awards

    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
     если
    -1.98
     refroid
    -1.93
     якщо
    -1.74
     rafraî
    -1.70
     tiveram
    -1.70
     estavam
    -1.63
     Perché
    -1.63
    姈
    -1.63
    谖
    -1.62
    鰾
    -1.61
    POSITIVE LOGITS
    >
    1.82
    '
    1.73
     of
    1.63
     therefore
    1.61
     thus
    1.55
     didn
    1.54
     ainsi
    1.53
    {
    1.52
     et
    1.52
     neither
    1.52
    Activations Density 0.003%

    No Known Activations