© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 21617
    Prev
    Next
    INDEX
    Explanations

    Latin phrases and vocabulary

    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
    ໊
    0.62
     شرطونو
    0.58
     कक्क
    0.57
     లేకుండా
    0.57
     హైదర్
    0.57
    㖣
    0.56
     চালাচ্ছে
    0.55
    ܸ
    0.55
     جوسینو
    0.54
    صالات
    0.54
    POSITIVE LOGITS
     etiam
    0.85
     quae
    0.82
     tamen
    0.82
     semper
    0.81
     quod
    0.80
     et
    0.79
     ut
    0.77
     nostri
    0.77
     nostra
    0.76
     eius
    0.76
    Activations Density 0.014%

    No Known Activations