© 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. 16-GEMMASCOPE-2-RES-262K
    7. 15101
    Prev
    Next
    INDEX
    Explanations

    improve

    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_16_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
     are
    1.14
    ли
    1.10
     as
    1.07
     In
    1.05
     }{\
    1.02
    0.97
     IMDb
    0.96
     alcanz
    0.96
     It
    0.95
     उपयोग
    0.94
    POSITIVE LOGITS
    ر
    1.54
    و
    1.41
    л
    1.35
    it
    1.33
    ت
    1.29
    ל
    1.29
    ский
    1.24
    ו
    1.21
    il
    1.18
    ین
    1.18
    Activations Density 0.038%

    No Known Activations