© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9135
    Prev
    Next
    INDEX
    Explanations

    figuring to sign

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Which
    0.48
     yang
    0.45
     which
    0.44
     A
    0.44
    0.44
     PDF
    0.43
    fas
    0.42
     Goodreads
    0.41
     หนึ่ง
    0.40
     who
    0.40
    POSITIVE LOGITS
    喜歡
    0.55
    欣賞
    0.45
     discussing
    0.45
    بيع
    0.45
     कामया
    0.44
    ňuje
    0.43
    忽略
    0.43
    が通販できます
    0.43
     કારણે
    0.42
    Ձ
    0.42
    Activations Density 0.005%

    No Known Activations