© 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. 114197
    Prev
    Next
    INDEX
    Explanations

    times involving "pm"

    np_acts-logits-general · gemini-2.5-flash-lite

    Russia's views on NATO

    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
     on
    0.58
     for
    0.53
     to
    0.50
    wa
    0.50
    camp
    0.49
    ówka
    0.48
    per
    0.46
     {
    0.46
    ço
    0.45
    stein
    0.44
    POSITIVE LOGITS
    ッフ
    0.51
    ))+\
    0.47
    ‼️
    0.47
     moldings
    0.47
     inodes
    0.47
     indiscrimin
    0.46
    EMANN
    0.46
     fulfillment
    0.45
     orientations
    0.45
     internacionales
    0.44
    Activations Density 0.000%

    No Known Activations