© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48904
    Prev
    Next
    INDEX
    Explanations

    American Indian history and culture

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

    The neuron fires on capitalized named‐entity tokens—people, organizations, places, titles, and dates/numbers.

    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
     tribe
    -0.85
    etches
    -0.84
     leader
    -0.79
    Sidenav
    -0.77
    edon
    -0.73
     Grandmother
    -0.73
     culture
    -0.72
     leaders
    -0.70
     tribal
    -0.70
    록
    -0.70
    POSITIVE LOGITS
     BIA
    0.87
     indien
    0.83
     LAND
    0.80
     hawa
    0.79
    Ụ
    0.78
    BIA
    0.78
     poë
    0.77
     kapa
    0.77
    шений
    0.77
     degust
    0.75
    Activations Density 0.026%

    No Known Activations