© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57034
    Prev
    Next
    INDEX
    Explanations

    companies and startups

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

    The neuron detects mentions of advising or investing in multiple companies or startups.

    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
    СТВ
    -0.81
    𝒆
    -0.79
    ʝ
    -0.79
    tamentos
    -0.78
    ুল
    -0.75
    anth
    -0.75
     mAdapter
    -0.73
    ⅽ
    -0.73
    nado
    -0.73
     комбини
    -0.70
    POSITIVE LOGITS
     startup
    3.89
     startups
    3.44
    startup
    2.98
     start
    2.89
     Startup
    2.67
    Startup
    2.63
     Startups
    2.20
     companies
    2.09
     Start
    2.03
     company
    1.99
    Activations Density 0.086%

    No Known Activations