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. 8111
    Prev
    Next
    INDEX
    Explanations

    integer types and questions

    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
     uint
    -1.27
    uint
    -1.15
     address
    -0.91
     addressing
    -0.90
     addresses
    -0.88
     addressed
    -0.85
    address
    -0.84
     mapping
    -0.80
     地址
    -0.76
    toli
    -0.75
    POSITIVE LOGITS
     int
    1.58
     Int
    1.45
    int
    1.34
     INT
    1.26
    Int
    1.15
    INT
    1.12
    getInt
    0.95
     intestine
    0.88
    Ctx
    0.85
     intestinal
    0.85
    Activations Density 0.025%

    No Known Activations