© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70658
    Prev
    Next
    INDEX
    Explanations

    rules, rights, lists, conventions, tool

    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
     EIGHT
    -1.11
    جميع
    -0.97
    ácido
    -0.96
     FOUR
    -0.96
     меры
    -0.96
     abbiamo
    -0.96
     TWENTY
    -0.93
    grafías
    -0.93
    times
    -0.93
    through
    -0.93
    POSITIVE LOGITS
     that
    1.13
     what
    1.06
    :
    1.00
    內的
    0.98
     this
    0.97
    攞
    0.95
    则
    0.93
    uari
    0.92
    uko
    0.90
     devenus
    0.90
    Activations Density 0.059%

    No Known Activations