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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75733
    Prev
    Next
    INDEX
    Explanations

    Canadian places and related entities

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

    The neuron detects terms and phrases describing political offices, elections, and government roles in a biographical or political context.

    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
    ⁝
    -1.05
     invitación
    -0.91
     fatig
    -0.88
     ২০১
    -0.87
    χυ
    -0.87
    евский
    -0.83
     inteligencia
    -0.82
     ilustración
    -0.81
    ohistochemistry
    -0.81
     HSBC
    -0.80
    POSITIVE LOGITS
     Handbuch
    0.82
     cucchiaio
    0.80
     уте
    0.80
     controlling
    0.78
    一九
    0.77
     昭和
    0.77
    مصادر
    0.76
    dı
    0.76
    рк
    0.74
     Reuter
    0.74
    Activations Density 0.064%

    No Known Activations