© 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. 183217
    Prev
    Next
    INDEX
    Explanations

    titles and follow-up punctuation

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

    Transformer, AI assistants, code formatting

    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
    ।
    0.67
    К
    0.66
    Пе
    0.64
    ТУ
    0.64
    ра
    0.63
    Кар
    0.63
    са
    0.62
     аналоги
    0.61
    Ста
    0.61
    а
    0.61
    POSITIVE LOGITS
     的
    1.08
     上
    0.94
     了
    0.82
     到
    0.80
     を
    0.79
     の
    0.76
     是
    0.75
     用
    0.75
     很
    0.75
     跟
    0.75
    Activations Density 0.027%

    No Known Activations