© 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. 34878
    Prev
    Next
    INDEX
    Explanations

    Society of organizations

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

    The neuron strongly activates on occurrences of the word “Society,” especially in the phrase “Society of …” as part of organization names.

    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
     entire
    -1.02
    鸶
    -0.93
    讓我
    -0.91
    をクリック
    -0.89
    ursales
    -0.88
    钧
    -0.87
    にあった
    -0.86
     circuitos
    -0.85
    peel
    -0.83
    regated
    -0.83
    POSITIVE LOGITS
     of
    1.08
    tese
    1.05
    ческими
    0.90
    وضع
    0.89
     Mijn
    0.88
     Widget
    0.86
     Autre
    0.86
    ﻚ
    0.85
    捍
    0.85
    ficamente
    0.85
    Activations Density 0.007%

    No Known Activations