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. 217
    Prev
    Next
    INDEX
    Explanations

    digital communication and services

    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
     because
    -1.63
     Because
    -1.38
     after
    -1.34
     during
    -1.34
     when
    -1.32
     although
    -1.30
     with
    -1.28
     in
    -1.25
     give
    -1.23
     will
    -1.22
    POSITIVE LOGITS
     Dinas
    1.51
     ...........
    1.37
     .........
    1.37
     ..........
    1.36
     colossal
    1.29
     pérd
    1.28
     alluring
    1.26
     gewi
    1.23
     faciliter
    1.23
     .......
    1.22
    Activations Density 0.138%

    No Known Activations