© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13255
    Prev
    Next
    INDEX
    Explanations

    intervals and pauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     ከሆነ
    1.04
    쁘
    0.96
    ῴ
    0.95
    handle
    0.95
    煒
    0.94
     handle
    0.94
    ようになる
    0.93
    맨
    0.93
    ਊ
    0.93
    lland
    0.93
    POSITIVE LOGITS
     STOP
    1.66
    stops
    1.56
     останов
    1.56
     stop
    1.55
     pauses
    1.54
     stops
    1.52
     Stop
    1.50
     Stops
    1.49
     intermission
    1.47
     Zwischen
    1.44
    Activations Density 0.254%

    No Known Activations