© 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. 31-GEMMASCOPE-2-RES-262K
    7. 15275
    Prev
    Next
    INDEX
    Explanations

    time, interval, message, border, background

    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_31_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
    确认
    0.41
    危机
    0.41
    宻
    0.40
     commissioned
    0.39
     सकुशल
    0.39
     হইয়াছিল
    0.39
    浻
    0.39
    钙
    0.38
     የም
    0.38
     administrativas
    0.38
    POSITIVE LOGITS
     shuffled
    0.39
     defeating
    0.38
     stacked
    0.37
    ibirsk
    0.37
     meats
    0.37
     garlic
    0.36
     stacking
    0.36
     synergy
    0.36
    heroes
    0.36
     strikers
    0.35
    Activations Density 0.028%

    No Known Activations