© 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. 20749
    Prev
    Next
    INDEX
    Explanations

    technical phrases

    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
     much
    -1.56
     will
    -1.55
     
    -1.52
     two
    -1.48
     “
    -1.43
     very
    -1.39
     more
    -1.38
     is
    -1.38
     widely
    -1.37
     regarded
    -1.37
    POSITIVE LOGITS
     huiles
    1.60
    brengen
    1.60
    bmatrix
    1.56
    millimeters
    1.52
     kommunizieren
    1.52
    То
    1.50
     veran
    1.48
    ódios
    1.46
     peruan
    1.45
    缂
    1.45
    Activations Density 0.269%

    No Known Activations