© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16020
    Prev
    Next
    INDEX
    Explanations

    Saint names and abbreviations

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

    spring boot web database metrics

    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_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
    attlist
    0.50
     vibhav
    0.48
    gheatmap
    0.47
     αλλά
    0.45
     −/−
    0.44
    ısı
    0.44
     वास्तविक
    0.44
     özellik
    0.44
    alım
    0.44
    residuals
    0.44
    POSITIVE LOGITS
     government
    0.55
    government
    0.54
    زاده
    0.52
    ز
    0.51
    ม
    0.49
    Government
    0.48
    Financial
    0.48
    azione
    0.47
    ک
    0.47
    ৫
    0.46
    Activations Density 0.053%

    No Known Activations