© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 36767
    Prev
    Next
    INDEX
    Explanations

    increasing higher and larger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     znacznie
    0.47
     своих
    0.42
     बजाय
    0.41
    uttosto
    0.39
    োনাল
    0.39
     potentially
    0.39
     considerably
    0.39
     ઘરે
    0.39
     comparatively
    0.38
    ❾
    0.37
    POSITIVE LOGITS
     increasing
    1.29
     Increasing
    1.27
    Increasing
    1.19
    increasing
    1.13
     higher
    1.06
     increase
    1.02
    higher
    1.02
     increases
    1.00
     увеличи
    1.00
     Higher
    1.00
    Activations Density 0.020%

    No Known Activations