© 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. 22-GEMMASCOPE-RES-131K
    7. 129819
    Prev
    Next
    INDEX
    Explanations

    programming view and http

    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
     Überras
    -1.08
    Приготовление
    -1.08
     each
    -0.96
    8
    -0.95
    uação
    -0.95
     universitaria
    -0.95
     послед
    -0.94
     extremely
    -0.92
     PopupWindow
    -0.92
     Actually
    -0.90
    POSITIVE LOGITS
     DEPARTMENT
    1.00
    Clik
    0.99
     человека
    0.98
    bject
    0.93
     entanto
    0.93
    억
    0.93
    kWh
    0.92
    Appellee
    0.92
    ceptar
    0.92
     roberto
    0.92
    Activations Density 0.002%

    No Known Activations