© 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. 111858
    Prev
    Next
    INDEX
    Explanations

    the [title]

    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
     krás
    -1.87
     těch
    -1.81
     salonu
    -1.81
     récolte
    -1.81
     detayl
    -1.80
     článku
    -1.77
     gethan
    -1.76
    錾
    -1.76
     rafraî
    -1.74
     čier
    -1.73
    POSITIVE LOGITS
     a
    2.83
     only
    2.03
     like
    2.03
     of
    1.95
    </h1>
    1.94
     even
    1.91
     ‘
    1.90
     in
    1.80
     will
    1.77
     Many
    1.70
    Activations Density 0.031%

    No Known Activations