© 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. 75339
    Prev
    Next
    INDEX
    Explanations

    includes and endings

    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
     пър
    -0.92
     first
    -0.91
    álny
    -0.90
     pierwszy
    -0.89
    初
    -0.87
     первом
    -0.86
     ersten
    -0.85
     первый
    -0.84
    viembre
    -0.83
    hezza
    -0.83
    POSITIVE LOGITS
     outro
    1.38
     ending
    1.17
    finishing
    1.14
     finishing
    1.11
     terminar
    1.09
     endblock
    1.08
    Ending
    1.06
     zakoń
    1.00
     Closing
    0.99
     concluding
    0.99
    Activations Density 0.001%

    No Known Activations