© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77909
    Prev
    Next
    INDEX
    Explanations

    tech, business, and finance entities

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

    The neuron detects corporate‐finance language, especially investment‐firm descriptions and related terminology like “private equity,” “capital,” “ventures,” and “investments.”

    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
    vies
    -0.83
     investors
    -0.81
    ОВ
    -0.81
     Investor
    -0.77
    Ng
    -0.76
    érience
    -0.76
    Investors
    -0.74
     شهاد
    -0.73
     Analysts
    -0.73
     analyst
    -0.72
    POSITIVE LOGITS
     businesses
    0.88
     брюки
    0.83
    žių
    0.82
    businesses
    0.80
    companies
    0.77
    preferably
    0.76
    داية
    0.75
     tait
    0.75
     tuli
    0.74
     situations
    0.73
    Activations Density 0.022%

    No Known Activations