© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62811
    Prev
    Next
    INDEX
    Explanations

    Native American lands and tribes

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

    The neuron detects mentions of Native American tribal or reservation entities and related official designations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Disponible
    -0.76
    Reklama
    -0.76
     mooi
    -0.74
     amarelo
    -0.71
     dedicada
    -0.70
    registro
    -0.70
    ../../../
    -0.69
     silnika
    -0.69
    ɺ
    -0.68
    chanter
    -0.68
    POSITIVE LOGITS
     trust
    1.18
    trust
    0.97
     tribe
    0.91
    lands
    0.88
    Trust
    0.88
     lands
    0.87
     Souver
    0.84
     fish
    0.82
     tribes
    0.82
     резер
    0.81
    Activations Density 0.012%

    No Known Activations