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. 7820
    Prev
    Next
    INDEX
    Explanations

    technical term followed by descriptor

    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
     simpel
    -1.79
     kader
    -1.76
     menant
    -1.75
     петербург
    -1.63
     abonnement
    -1.61
     siè
    -1.61
     uly
    -1.58
     phénom
    -1.57
     ſol
    -1.55
     berge
    -1.55
    POSITIVE LOGITS
     information
    2.33
     analysis
    2.09
     versus
    2.03
     considerations
    2.02
     data
    2.02
     to
    1.97
     problems
    1.89
     evaluation
    1.89
     vs
    1.88
     -
    1.84
    Activations Density 0.212%

    No Known Activations