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. 8171
    Prev
    Next
    INDEX
    Explanations

    In addition

    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
     one
    -1.50
     which
    -1.43
     for
    -1.18
     both
    -1.11
     at
    -1.03
     while
    -1.02
     a
    -0.99
     melawan
    -0.94
     if
    -0.93
     other
    -0.93
    POSITIVE LOGITS
     wszystko
    1.09
     eftersom
    0.99
    wußt
    0.97
     joining
    0.93
     ponieważ
    0.93
    顺着
    0.92
     undertaking
    0.92
    jot
    0.92
     bén
    0.92
    tillation
    0.91
    Activations Density 0.043%

    No Known Activations