© 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. 167992
    Prev
    Next
    INDEX
    Explanations

    known facts or specific examples

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

    conditional logic and structures

    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
    のこ
    0.49
     Ради
    0.49
    плом
    0.47
    ຈາກ
    0.46
    против
    0.46
     fasted
    0.46
    </h3>
    0.45
     Кра
    0.45
    тури
    0.45
    ❁
    0.45
    POSITIVE LOGITS
     ẩm
    0.51
     ẩn
    0.48
     rů
    0.48
     jederzeit
    0.47
    alnız
    0.46
     geplant
    0.46
     lành
    0.45
    punkte
    0.44
    ું
    0.44
     gön
    0.44
    Activations Density 0.000%

    No Known Activations