© 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. 34-GEMMASCOPE-RES-131K
    7. 47530
    Prev
    Next
    INDEX
    Explanations

    code function definitions

    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_34/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
     Ucraina
    -0.96
    Отзывы
    -0.94
     égard
    -0.91
     kafe
    -0.90
     kristal
    -0.87
     comté
    -0.86
    ángulo
    -0.86
     disrupted
    -0.86
     vixion
    -0.86
    −/−
    -0.85
    POSITIVE LOGITS
     (
    1.27
     ensure
    1.11
     function
    1.11
     async
    1.05
     verify
    0.93
     [
    0.84
     /*
    0.82
     ((
    0.82
     )
    0.82
     Verify
    0.81
    Activations Density 0.002%

    No Known Activations