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. 8238
    Prev
    Next
    INDEX
    Explanations

    due diligence

    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
     Depending
    -1.06
     Because
    -0.96
     Dispens
    -0.90
     Deploy
    -0.90
     Derived
    -0.89
     During
    -0.87
    Deploy
    -0.85
     Deployment
    -0.85
     Debt
    -0.85
     Depression
    -0.85
    POSITIVE LOGITS
     due
    2.56
     du
    1.18
     dus
    1.14
     دو
    1.10
     debido
    1.08
    Due
    1.05
     dua
    1.05
     duo
    1.05
    由于
    1.02
     devido
    0.99
    Activations Density 0.090%

    No Known Activations