© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119035
    Prev
    Next
    INDEX
    Explanations

    marketing for businesses

    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
    edere
    -0.95
    ftar
    -0.87
    emand
    -0.79
    nyard
    -0.79
    ígenes
    -0.76
    pergillus
    -0.76
    ńskiej
    -0.73
    chetto
    -0.73
     informática
    -0.73
    inine
    -0.73
    POSITIVE LOGITS
     businesses
    2.52
     small
    1.90
     business
    1.87
     SMB
    1.59
    small
    1.52
     brands
    1.50
    Businesses
    1.41
    businesses
    1.40
     companies
    1.37
     brand
    1.29
    Activations Density 0.063%

    No Known Activations