© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72659
    Prev
    Next
    INDEX
    Explanations

    solutions, extend, ideas, view, patiently, polling, game, flights

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

    checks and ownership

    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_31_width_262k_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
     ziemlich
    0.39
     весьма
    0.37
     тщательно
    0.37
     наконец
    0.36
     entusiasmo
    0.36
     प्रॉब्लम
    0.36
    о
    0.35
    яна
    0.35
    бята
    0.35
    다
    0.35
    POSITIVE LOGITS
     এইরূপ
    0.48
     therefore
    0.44
    所以在
    0.42
     এছাড়াও
    0.39
     pertanto
    0.39
     বলেও
    0.38
     इसलिए
    0.38
     incluyendo
    0.37
     এইভাবে
    0.37
     somit
    0.37
    Activations Density 0.300%

    No Known Activations