© 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. 191172
    Prev
    Next
    INDEX
    Explanations

    titles and headings

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

    **punctuation and missing deadlines**

    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
    a
    0.51
    render
    0.47
     a
    0.47
     самих
    0.46
    relation
    0.46
    wer
    0.45
    Result
    0.45
    畂
    0.44
    Reduce
    0.44
    ”)
    0.43
    POSITIVE LOGITS
     berhenti
    0.55
     judul
    0.51
     intitulé
    0.47
     intitul
    0.46
     TITLE
    0.46
    츈
    0.45
    iunea
    0.45
     istilah
    0.45
     tit
    0.44
    タイトル
    0.44
    Activations Density 0.001%

    No Known Activations