© 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. 226842
    Prev
    Next
    INDEX
    Explanations

    abortion, pregnancy, and medical terms

    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
     arena
    0.47
     Arena
    0.46
     MOB
    0.45
     però
    0.45
    ในสนาม
    0.45
    ৪
    0.45
     Pasteur
    0.44
     ज़रूर
    0.44
     ост
    0.44
     Amnesty
    0.43
    POSITIVE LOGITS
    금
    0.51
    make
    0.45
    S
    0.45
    沂
    0.45
    forestation
    0.44
    Chhattisgarh
    0.42
    渔
    0.42
     결방
    0.42
    subsec
    0.41
    slave
    0.41
    Activations Density 0.000%

    No Known Activations