© 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. 185050
    Prev
    Next
    INDEX
    Explanations

    parts of speech markers

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

    deadlocks, standard, abandoned, same

    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
    Negative Logits
     वोल्टेज
    0.51
     осозна
    0.50
    羯
    0.49
    炬
    0.48
    意识到
    0.47
    チャレンジ
    0.47
     созна
    0.46
     سعی
    0.46
     অন্তত
    0.46
    ほしい
    0.45
    POSITIVE LOGITS
    xsi
    0.46
    heba
    0.45
    \{-
    0.45
    vah
    0.44
     dada
    0.44
    algebras
    0.43
    ifu
    0.43
     svog
    0.43
    fov
    0.42
    ﺡ
    0.42
    Activations Density 0.000%

    No Known Activations