© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12198
    Prev
    Next
    INDEX
    Explanations

    cache eviction replacement policy

    np_acts-logits-general · gemini-2.5-flash-lite

    diagrams and code sequences

    np_acts-logits-general · gemini-2.5-flash-lite

    2

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    graphql
    0.43
     proteinuria
    0.43
    brigen
    0.43
    лата
    0.42
     exertion
    0.42
     hardship
    0.42
    
    0.41
    ೋಜನ
    0.41
    stagram
    0.41
    গন্ধ
    0.41
    POSITIVE LOGITS
     illustrated
    0.50
     shown
    0.49
     क
    0.48
     க
    0.47
    shown
    0.47
    र
    0.47
     la
    0.46
     benda
    0.45
     Illustrated
    0.45
     workpiece
    0.45
    Activations Density 0.152%

    No Known Activations