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. 8098
    Prev
    Next
    INDEX
    Explanations

    names of fields

    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
    lastName
    -1.41
     lastName
    -1.32
    LastName
    -1.28
     Surname
    -1.23
     LastName
    -1.21
    surname
    -1.18
     lastname
    -1.13
     surname
    -1.13
    Surname
    -1.09
    lastname
    -1.07
    POSITIVE LOGITS
     middle
    1.11
     Middle
    1.07
     company
    1.02
     Company
    1.02
     Street
    0.94
    middle
    0.93
     email
    0.91
    MIDDLE
    0.89
     street
    0.89
    suffix
    0.85
    Activations Density 0.013%

    No Known Activations