© 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-262K
    7. 122751
    Prev
    Next
    INDEX
    Explanations

    quality metrics

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

    evaluating performance and progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     disgr
    0.49
     बरस
    0.45
    pyrrolo
    0.43
    neet
    0.43
     ಹಿಂದ
    0.43
    jag
    0.43
     शोध
    0.42
     ',');
    0.42
     Jahre
    0.42
    rias
    0.42
    POSITIVE LOGITS
     المدينة
    0.52
     geotechnical
    0.49
     Esports
    0.48
     Amtrak
    0.46
     autoplay
    0.43
     Outback
    0.43
     également
    0.43
     optomet
    0.42
     autonom
    0.41
     City
    0.41
    Activations Density 0.003%

    No Known Activations