© 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. 63697
    Prev
    Next
    INDEX
    Explanations

    immigration violations

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

    extremism, piece, scenario, date, masa

    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
    wall
    0.54
    mani
    0.47
    most
    0.47
    il
    0.45
    g
    0.44
    human
    0.42
    irg
    0.41
    him
    0.41
    rott
    0.40
    onal
    0.40
    POSITIVE LOGITS
    Scenario
    0.51
    䤃
    0.49
    আন্তর্জাতিক
    0.49
     கல்லற
    0.48
     listView
    0.48
     încep
    0.47
     hazırl
    0.46
     thisTrack
    0.45
    সুতরাং
    0.45
    TRANSPORT
    0.44
    Activations Density 0.000%

    No Known Activations