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. 8263
    Prev
    Next
    INDEX
    Explanations

    AutoLayout, Daily Mail, Virtual Machines, RabbitMQ, Marketing cloud

    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
    iaal
    -1.70
    Sadly
    -1.65
    Thankfully
    -1.61
    不仅
    -1.55
    toir
    -1.51
    Также
    -1.50
     locura
    -1.48
     maniere
    -1.47
     perceptible
    -1.45
    Warum
    -1.44
    POSITIVE LOGITS
     their
    1.84
     at
    1.70
     in
    1.67
     In
    1.63
     an
    1.60
     before
    1.58
     when
    1.50
     often
    1.50
     had
    1.49
     this
    1.45
    Activations Density 0.254%

    No Known Activations