© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82865
    Prev
    Next
    INDEX
    Explanations

    company names and corporations

    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
    iência
    -0.75
    Numer
    -0.75
     jetzt
    -0.73
     Seller
    -0.72
    epsilon
    -0.71
    これから
    -0.71
    setVerticalGroup
    -0.71
     Consultado
    -0.70
     künst
    -0.70
    ulic
    -0.69
    POSITIVE LOGITS
     Company
    1.13
     Chase
    0.96
    Company
    0.92
     Compton
    0.91
     Co
    0.86
    Chase
    0.84
    chase
    0.80
     company
    0.74
     wako
    0.73
     COMPANY
    0.70
    Activations Density 0.052%

    No Known Activations