© 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. 41-GEMMASCOPE-2-RES-262K
    7. 26663
    Prev
    Next
    INDEX
    Explanations

    leaving age or card

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    +](=
    0.39
     softens
    0.38
    ampled
    0.38
     browned
    0.35
    atif
    0.35
    led
    0.35
    ticks
    0.35
    ],[
    0.34
    ȏ
    0.33
     segundos
    0.33
    POSITIVE LOGITS
     leaving
    1.80
     leave
    1.66
     Leaving
    1.63
    Leaving
    1.63
    leaving
    1.63
     Leave
    1.59
    Leave
    1.57
     оставля
    1.53
    leave
    1.45
     оставить
    1.44
    Activations Density 0.001%

    No Known Activations