© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13920
    Prev
    Next
    INDEX
    Explanations

    information on various topics

    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
    descriptions
    0.41
    เตอร์
    0.37
     Descriptions
    0.37
    
    0.37
     copies
    0.37
     설명
    0.37
    报道
    0.36
    ↵↵↵↵↵↵
    0.35
    었고
    0.35
     இருக்கிறார்
    0.35
    POSITIVE LOGITS
     topics
    0.87
     how
    0.86
     behalf
    0.82
     വിഷയ
    0.73
     matters
    0.72
     كيفية
    0.70
     subjects
    0.69
    如何
    0.69
     why
    0.68
    how
    0.67
    Activations Density 0.005%

    No Known Activations