© 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. 98335
    Prev
    Next
    INDEX
    Explanations

    abandoned or left behind

    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
    Blurred
    0.43
     Livermore
    0.40
    ultipl
    0.39
    隐私
    0.38
    吅
    0.38
    blurred
    0.38
    }\|^{
    0.37
     নির্ধার
    0.37
    臥
    0.36
    )|^{
    0.35
    POSITIVE LOGITS
     abandonment
    1.91
     abandoned
    1.86
     abandon
    1.80
     aband
    1.71
     Abandon
    1.71
     abband
    1.71
    abandon
    1.66
    Abandon
    1.66
     abandoning
    1.64
    Abandoned
    1.59
    Activations Density 0.001%

    No Known Activations