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. 120
    Prev
    Next
    INDEX
    Explanations

    structured code snippets

    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
     despite
    -1.20
     for
    -1.16
     because
    -1.13
     there
    -1.05
     not
    -1.04
     their
    -1.03
     get
    -1.00
     or
    -0.98
     new
    -0.96
     Taking
    -0.96
    POSITIVE LOGITS
     meisten
    1.05
     sooo
    0.94
    selben
    0.94
     BLA
    0.88
     molti
    0.88
    鹬
    0.87
     creș
    0.85
     ayur
    0.85
     soooo
    0.85
     wonderfully
    0.85
    Activations Density 0.001%

    No Known Activations