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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8520
    Prev
    Next
    INDEX
    Explanations

    links and code

    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
     cabe
    -0.97
     Люди
    -0.86
     reais
    -0.85
     Pute
    -0.84
     itens
    -0.83
    membered
    -0.80
    возмо
    -0.79
     fiel
    -0.79
     питання
    -0.79
     atu
    -0.79
    POSITIVE LOGITS
     înal
    0.96
     gră
    0.95
    argli
    0.88
    ordinateur
    0.88
     pregă
    0.83
     aufgeführt
    0.83
     dreary
    0.82
     clés
    0.82
    EDIA
    0.82
     geliefert
    0.82
    Activations Density 0.001%

    No Known Activations