© 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. 226868
    Prev
    Next
    INDEX
    Explanations

    geopolitical actors, specific locations

    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
    1
    0.54
    w
    0.54
    with
    0.52
    Al
    0.51
    met
    0.51
    Far
    0.51
    h
    0.51
    v
    0.51
    bar
    0.50
    vi
    0.50
    POSITIVE LOGITS
     paces
    0.52
     площадь
    0.51
     subspaces
    0.51
     год
    0.50
    젹
    0.50
     hướng
    0.50
    विद्या
    0.49
     forested
    0.48
     shy
    0.48
    parsedBlock
    0.46
    Activations Density 0.000%

    No Known Activations