© 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-16K
    7. 11367
    Prev
    Next
    INDEX
    Explanations

    punctuation and following words

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

    examples, code, questions

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    려
    0.60
     headwinds
    0.59
    3
    0.57
    혔
    0.53
    들
    0.52
     ㄹ
    0.52
    넬
    0.52
    았습니다
    0.50
    0.50
    쳤
    0.50
    POSITIVE LOGITS
    ऐसे
    0.61
     peculiarity
    0.61
    あるいは
    0.60
    Khi
    0.58
    けれど
    0.58
    রচনা
    0.57
     কিংবা
    0.56
    অর্থাৎ
    0.56
    Từ
    0.55
    Với
    0.55
    Activations Density 0.052%

    No Known Activations