© 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. 128923
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     [{
    -1.14
    ☆☆☆☆☆
    -1.09
    عنوان
    -1.07
    تحميل
    -1.04
     __('
    -1.04
    řejmě
    -1.02
     baterie
    -1.02
    >?
    -1.01
     некото
    -1.00
    ̊
    -1.00
    POSITIVE LOGITS
     umfasst
    1.10
     are
    1.05
     does
    1.04
     you
    1.04
     таком
    1.01
     these
    1.00
    んですよね
    0.97
    5
    0.96
     finition
    0.95
    www
    0.94
    Activations Density 0.024%

    No Known Activations