© 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. 13483
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
     fuimos
    -2.02
     kleines
    -1.83
    栊
    -1.72
     estábamos
    -1.66
    岽
    -1.65
     gewöhn
    -1.63
     besonderes
    -1.62
     Aktionen
    -1.61
    ேன்
    -1.61
    𞤢
    -1.55
    POSITIVE LOGITS
    al
    2.02
    {
    2.00
     You
    1.97
    re
    1.81
    y
    1.77
    mathrm
    1.76
    at
    1.73
    IN
    1.70
     seems
    1.66
    er
    1.64
    Activations Density 0.003%

    No Known Activations