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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7681
    Prev
    Next
    INDEX
    Explanations

    technical questions and answers

    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
     just
    -0.82
     on
    -0.82
    зывают
    -0.81
     slight
    -0.80
     widespread
    -0.80
     enhancing
    -0.80
     changes
    -0.79
     enhanced
    -0.78
     broken
    -0.77
     enhance
    -0.77
    POSITIVE LOGITS
     Internship
    1.08
     vitam
    1.05
    actually
    1.00
    ήσει
    0.98
     viewDidLoad
    0.96
     professeur
    0.94
     demokra
    0.92
     Fuente
    0.92
     Newtonsoft
    0.91
    translator
    0.90
    Activations Density 0.000%

    No Known Activations