© 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. 118033
    Prev
    Next
    INDEX
    Explanations

    personal debt, international threat, foreign families

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

    internet, online, forums

    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
    t
    0.49
    ت
    0.49
    tet
    0.49
     cords
    0.48
     Pug
    0.48
    with
    0.47
    ات
    0.47
    də
    0.46
    d
    0.45
     Gull
    0.45
    POSITIVE LOGITS
    HARAD
    0.54
    neş
    0.51
    Naissance
    0.50
    ાન
    0.50
    ાસ
    0.49
    ști
    0.48
     सिसोदिया
    0.48
     helplessly
    0.47
    ības
    0.47
    ScrollPane
    0.46
    Activations Density 0.000%

    No Known Activations