© 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. 99082
    Prev
    Next
    INDEX
    Explanations

    company and accompanying

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

    The neuron detects words and phrases that signal mutual companionship or togetherness (e.g. “making,” “keeping,” “each other,” “company,” “people”).

    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
    connector
    -0.73
    篡
    -0.69
     нала
    -0.68
    っちゃう
    -0.67
    incorpor
    -0.66
     eingerichtet
    -0.63
    olyn
    -0.63
    Copies
    -0.62
    lägg
    -0.62
    bronn
    -0.61
    POSITIVE LOGITS
     company
    4.63
    company
    3.81
     companionship
    3.70
     compañía
    3.61
     accompany
    3.42
     companhia
    3.33
    Company
    3.20
     companion
    3.17
     companions
    3.13
    COMPANY
    3.06
    Activations Density 0.053%

    No Known Activations