Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 40
    Prev
    Next
    INDEX
    Explanations

    economic sense or viability

    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
     berichten
    -0.96
     klicken
    -0.90
     respekt
    -0.83
    atko
    -0.81
     growled
    -0.81
    olalar
    -0.79
    łat
    -0.77
    gisi
    -0.77
     citas
    -0.77
    illère
    -0.77
    POSITIVE LOGITS
     economics
    2.67
     economic
    2.59
     economically
    2.44
     economical
    2.27
     Economics
    2.09
     profitable
    2.00
     cost
    1.99
    economics
    1.99
    econom
    1.98
     экономи
    1.96
    Activations Density 0.075%

    No Known Activations