© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 489
    Prev
    Next
    INDEX
    Explanations

    examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ograp
    0.44
    চ্ছা
    0.39
     পরিকল্প
    0.36
     கூறும்
    0.36
    秥
    0.35
    offre
    0.34
    𝖑
    0.34
    搅拌
    0.34
    全面的
    0.34
     výbě
    0.34
    POSITIVE LOGITS
     Examples
    0.75
    例子
    0.75
    Examples
    0.74
     examples
    0.73
     example
    0.72
    examples
    0.70
     Beispiele
    0.70
     Rules
    0.70
     exemplos
    0.68
    示例
    0.68
    Activations Density 0.067%

    No Known Activations