© 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. 129733
    Prev
    Next
    INDEX
    Explanations

    after time

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

    at the start of descriptions

    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
     Нико
    0.54
     Благодаря
    0.51
     돌아
    0.49
     tonos
    0.48
     గ
    0.47
     భార
    0.46
     няко
    0.46
     zwar
    0.45
     тамо
    0.45
     circumst
    0.45
    POSITIVE LOGITS
     posto
    0.46
     TREND
    0.46
    ഹ
    0.43
    อบ
    0.41
     diffusione
    0.41
     crumble
    0.41
     espresso
    0.40
    ਸ
    0.40
     disable
    0.40
     COMMERCIAL
    0.40
    Activations Density 0.000%

    No Known Activations