© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22564
    Prev
    Next
    INDEX
    Explanations

    chocolate treats and cake

    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
     রোহিঙ্গাদের
    0.47
    沤
    0.46
     VPN
    0.45
    饭
    0.44
    樯
    0.41
    탉
    0.41
    дентифика
    0.40
    راحی
    0.40
    Xml
    0.39
     Ethernet
    0.38
    POSITIVE LOGITS
     chocolate
    2.25
    🍫
    2.08
     Chocolate
    2.05
    Chocolate
    2.05
     chocolates
    2.03
     шокола
    2.00
    chocolate
    1.98
     candy
    1.97
     chocolat
    1.97
     chocol
    1.95
    Activations Density 0.054%

    No Known Activations