© 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. 16-GEMMASCOPE-2-RES-16K
    7. 521
    Prev
    Next
    INDEX
    Explanations

    parentheses and percentages

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

    code punctuation like brackets and parentheses

    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_16_width_16k_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
    :
    0.59
    ;
    0.46
    ۔
    0.34
     for
    0.33
    :”
    0.32
     gingham
    0.32
    *;
    0.31
    ;*/
    0.30
     outfitted
    0.30
     remastered
    0.30
    POSITIVE LOGITS
    ل
    0.49
    л
    0.35
     porcentaje
    0.33
     argumento
    0.33
    仞
    0.33
     risiko
    0.33
     nervioso
    0.32
    ল
    0.31
     bepa
    0.30
     dieren
    0.30
    Activations Density 0.199%

    No Known Activations