© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74873
    Prev
    Next
    INDEX
    Explanations

    product waste

    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
    鋐
    0.55
     বিস্তারিত
    0.49
     அழ
    0.47
     രാജ്യ
    0.47
    覬
    0.46
     عنصر
    0.45
     ]))
    0.45
     anlaş
    0.45
     ব্রাজ
    0.45
     rifer
    0.44
    POSITIVE LOGITS
     shutout
    0.46
    Mercury
    0.45
    {
    0.44
    Sync
    0.44
    Squirrel
    0.43
    Name
    0.43
    Ko
    0.43
    I
    0.43
    Keep
    0.42
     shut
    0.42
    Activations Density 0.013%

    No Known Activations