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. 8350
    Prev
    Next
    INDEX
    Explanations

    numbers and code delimiters

    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
     svoju
    -0.99
     objav
    -0.95
     najlep
    -0.94
     adresu
    -0.89
     undersø
    -0.88
     množ
    -0.87
     inš
    -0.86
     prič
    -0.86
     počas
    -0.85
     that
    -0.84
    POSITIVE LOGITS
     ナイロン
    0.95
    ällor
    0.94
    hline
    0.91
     maravilhoso
    0.91
     dlou
    0.90
     flourishing
    0.90
    Jen
    0.90
     hesitation
    0.90
    Ji
    0.89
     Shr
    0.88
    Activations Density 0.002%

    No Known Activations