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. 8485
    Prev
    Next
    INDEX
    Explanations

    business concepts and their applications

    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
    issues
    -0.83
     alternativa
    -0.82
     malah
    -0.81
    صدار
    -0.79
    latimes
    -0.79
     regarding
    -0.77
    Marg
    -0.76
     innovative
    -0.76
    ,"%
    -0.75
    手順
    -0.75
    POSITIVE LOGITS
     pprint
    0.92
     flywheel
    0.91
    efe
    0.90
    ƌ
    0.90
     EconPapers
    0.88
    lining
    0.88
    vereignty
    0.88
     sherpa
    0.85
    ionization
    0.85
     cadence
    0.84
    Activations Density 0.045%

    No Known Activations