© 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. 118193
    Prev
    Next
    INDEX
    Explanations

    self-employed freelancers sole traders

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

    The neuron strongly activates on mentions of “self-employed” (i.e. references to self-employment status).

    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
     aberto
    -0.79
    insider
    -0.76
    🏈
    -0.75
    ಊ
    -0.72
     Ugo
    -0.72
    Insider
    -0.71
    čio
    -0.71
    idings
    -0.71
    getX
    -0.70
    engel
    -0.70
    POSITIVE LOGITS
     self
    3.34
     Self
    2.42
     freelance
    2.41
    Self
    2.33
    self
    2.27
     само
    2.02
    自
    1.95
     freel
    1.91
     freelancer
    1.91
     freelancers
    1.84
    Activations Density 0.031%

    No Known Activations