© 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-16K
    7. 11806
    Prev
    Next
    INDEX
    Explanations

    struggling with

    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_16k_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
    צ
    0.38
    ٠
    0.37
     rằng
    0.37
     utvik
    0.36
    زا
    0.35
     çık
    0.34
    ում
    0.34
    系統
    0.34
     udvik
    0.33
     bahwa
    0.33
    POSITIVE LOGITS
     names
    0.41
    handles
    0.40
     rufo
    0.40
    fruits
    0.39
    a
    0.39
    
    0.39
     названия
    0.38
     cloves
    0.38
     ASCII
    0.37
     რომელი
    0.37
    Activations Density 0.041%

    No Known Activations