© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6916
    Prev
    Next
    INDEX
    Explanations

    cooperative groups and associations

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

    The neuron detects multi‐word compound noun phrases—especially formal or hyphenated technical terms (e.g. “mutual-aid health insurance,” “star-forming region,” “self-governing association”).

    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
    ITUTE
    -0.87
     national
    -0.82
     Report
    -0.79
     блу
    -0.78
    écial
    -0.78
     Suite
    -0.77
     published
    -0.76
     presenza
    -0.74
    orth
    -0.74
     страну
    -0.72
    POSITIVE LOGITS
     cooperative
    1.91
     groups
    1.85
     cooperatives
    1.81
     association
    1.79
     group
    1.60
     associations
    1.58
     Cooperative
    1.38
     collective
    1.37
    groups
    1.36
    cooperative
    1.36
    Activations Density 0.018%

    No Known Activations