© 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. 60087
    Prev
    Next
    INDEX
    Explanations

    Merlin, Pendragon, Arthurian legend

    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
     hebben
    -2.05
    ︕
    -1.99
     funcionarios
    -1.85
    遢
    -1.85
    跸
    -1.83
     disponibilités
    -1.74
    檍
    -1.74
    </h3>
    -1.73
     visites
    -1.72
     franceses
    -1.70
    POSITIVE LOGITS
    <
    1.95
     only
    1.77
     Only
    1.74
     Not
    1.67
    但不
    1.62
     well
    1.59
    ستارهای
    1.59
     不
    1.58
    The
    1.57
     How
    1.55
    Activations Density 0.009%

    No Known Activations