© 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. 7053
    Prev
    Next
    INDEX
    Explanations

    entrepreneurship and business

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

    The neuron strongly activates on numbers and numeric quantity words (e.g. digits, years, counts like “twenty,” “five,” etc.).

    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
    çam
    -0.88
     recrutement
    -0.88
    بيت
    -0.88
    werking
    -0.85
    payers
    -0.85
    memberOf
    -0.84
    کات
    -0.84
    brane
    -0.81
     علوم
    -0.81
    ⓐ
    -0.81
    POSITIVE LOGITS
     entrepreneurs
    5.16
     entrepreneurial
    4.34
     entrepreneur
    4.25
     Entrepreneurs
    3.86
     business
    3.31
     Entrepreneur
    3.28
    Entre
    3.02
    entrepreneur
    3.02
     предпринима
    2.95
     Entrepre
    2.92
    Activations Density 0.093%

    No Known Activations