© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 224856
    Prev
    Next
    INDEX
    Explanations

    foreign and indigenous peoples

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

    data, graphs, database

    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
    Not in Any Lists

    No Comments

    Negative Logits
    一位
    0.45
     gim
    0.44
    用途
    0.43
    0.43
    评价
    0.43
    чём
    0.42
    unz
    0.41
    니
    0.41
    ниш
    0.40
    erler
    0.40
    POSITIVE LOGITS
     सेंसर
    0.52
     subgraph
    0.45
     daemon
    0.43
     Natives
    0.43
     beforehand
    0.42
     boson
    0.42
    getMeteringAreas
    0.42
    Indigenous
    0.42
     السابق
    0.42
     እንኳ
    0.42
    Activations Density 0.000%

    No Known Activations