© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62446
    Prev
    Next
    INDEX
    Explanations

    break or pause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    CROSSTALK
    -0.83
    jami
    -0.80
    mended
    -0.76
    paña
    -0.75
    λία
    -0.73
    {?>
    -0.73
    vant
    -0.73
     touristique
    -0.71
    ACHEL
    -0.68
    ležité
    -0.68
    POSITIVE LOGITS
     break
    6.00
     breaks
    5.69
    break
    4.63
     Break
    4.38
     Breaks
    4.22
    Break
    4.13
    breaks
    4.03
     BREAK
    3.75
    BREAK
    3.64
     pause
    3.11
    Activations Density 0.070%

    No Known Activations