© 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-65K
    7. 3319
    Prev
    Next
    INDEX
    Explanations

    breakdown, ropes, flash

    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_65k_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
    餘
    0.49
    随着
    0.45
    ט
    0.44
    色的
    0.44
    則是
    0.44
     dần
    0.43
    то
    0.42
    隨著
    0.42
     لە
    0.42
    這是
    0.42
    POSITIVE LOGITS
     hurd
    0.50
     corvette
    0.50
    u
    0.48
     canyons
    0.47
    köy
    0.46
     dryers
    0.46
     planters
    0.46
    inol
    0.45
     cadets
    0.45
     çocuklar
    0.45
    Activations Density 0.003%

    No Known Activations