© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25461
    Prev
    Next
    INDEX
    Explanations

    technical code and data structures

    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_22/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
     ortam
    -0.99
     diğer
    -0.95
     outras
    -0.93
     juez
    -0.91
    wortet
    -0.90
    atangan
    -0.90
    你在
    -0.88
     zudem
    -0.88
     umfang
    -0.88
    他说
    -0.87
    POSITIVE LOGITS
    omsday
    1.16
    tifiable
    1.16
     februari
    1.16
     प्रोड
    1.13
    tembro
    1.13
    ofre
    1.12
     febru
    1.11
    vého
    1.09
     mikina
    1.08
     which
    1.07
    Activations Density 0.137%

    No Known Activations