© 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. 130175
    Prev
    Next
    INDEX
    Explanations

    words starting with "Und"

    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
     staring
    0.43
     below
    0.42
    చు
    0.40
     dependence
    0.39
     resistive
    0.39
     नीचे
    0.39
     stare
    0.38
     replica
    0.38
     starry
    0.38
     亠
    0.38
    POSITIVE LOGITS
    Und
    0.93
     Und
    0.90
     UND
    0.72
     und
    0.64
    und
    0.57
    UND
    0.57
     undes
    0.54
     vnd
    0.50
    undu
    0.48
     Unde
    0.48
    Activations Density 0.005%

    No Known Activations