© 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. 63864
    Prev
    Next
    INDEX
    Explanations

    business and industry concepts

    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
    farma
    -0.82
     emperors
    -0.81
    rpg
    -0.80
    Ҫ
    -0.79
     Nasdaq
    -0.77
    ofluorescence
    -0.76
     leyendas
    -0.75
     hamsters
    -0.74
     宝宝
    -0.72
     leggings
    -0.71
    POSITIVE LOGITS
     value
    1.07
     buyers
    0.94
     buyer
    0.93
    Buyer
    0.93
     Buyer
    0.93
     industry
    0.93
     Value
    0.84
     Industry
    0.82
     Generic
    0.81
     Por
    0.81
    Activations Density 0.006%

    No Known Activations