© 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. 103909
    Prev
    Next
    INDEX
    Explanations

    investment

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    หนัก
    -0.82
     весело
    -0.78
    卸载
    -0.73
     deserto
    -0.73
     antwortete
    -0.73
    gig
    -0.72
     البشر
    -0.72
    indicato
    -0.71
     behaup
    -0.71
    सन्दर्भ
    -0.71
    POSITIVE LOGITS
     investors
    1.90
     investor
    1.72
     Investor
    1.50
     investment
    1.42
    Investor
    1.35
     Investors
    1.30
     инвести
    1.30
    investor
    1.29
     Investment
    1.27
    investment
    1.27
    Activations Density 0.003%

    No Known Activations