© 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. 143060
    Prev
    Next
    INDEX
    Explanations

    codified and asked

    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
    博士
    0.45
    طلاق
    0.44
    ,+\
    0.42
    ,+
    0.42
    سك
    0.41
    Ди
    0.41
     الط
    0.40
     ড
    0.40
     آواز
    0.40
     तलाक
    0.40
    POSITIVE LOGITS
     does
    0.44
     sampai
    0.42
     jika
    0.41
     locking
    0.40
     configurable
    0.40
     Ix
    0.39
     adjustable
    0.39
     jargon
    0.39
     welding
    0.39
     අඩු
    0.39
    Activations Density 0.003%

    No Known Activations