© 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. 187078
    Prev
    Next
    INDEX
    Explanations

    progresses, strengthens, or continues

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

    analysis and improvement

    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
    vasena
    0.54
     تاریخ
    0.52
     ধরা
    0.51
     이해
    0.49
     그다
    0.48
     Национа
    0.48
    𒄿
    0.48
    ጲ
    0.48
    ЛЬ
    0.47
     理解
    0.47
    POSITIVE LOGITS
     strengthens
    0.57
     progresses
    0.49
     reinforces
    0.47
     widths
    0.45
     progressing
    0.45
    resti
    0.44
    ę
    0.44
     silently
    0.44
    •
    0.44
     divergences
    0.43
    Activations Density 0.000%

    No Known Activations