© 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. 73474
    Prev
    Next
    INDEX
    Explanations

    election Day

    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
    %/
    -0.93
    пустить
    -0.93
    🚐
    -0.92
    ραπε
    -0.91
    難易
    -0.91
    这一幕
    -0.90
    ڳ
    -0.90
     altitudes
    -0.90
    ogues
    -0.89
    ++.
    -0.88
    POSITIVE LOGITS
     its
    1.20
    karet
    0.96
     treff
    0.92
    سين
    0.90
     Then
    0.90
     Этот
    0.90
     enth
    0.89
     grü
    0.88
    Medi
    0.88
     retten
    0.87
    Activations Density 0.003%

    No Known Activations