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. 186
    Prev
    Next
    INDEX
    Explanations

    version or affiliates

    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
     which
    -0.98
     Whip
    -0.87
     their
    -0.84
    erkek
    -0.76
     pēc
    -0.75
     darbu
    -0.75
     that
    -0.75
     on
    -0.74
    に行ってきました
    -0.74
     республики
    -0.74
    POSITIVE LOGITS
    idemia
    0.84
    ech
    0.80
     SRT
    0.79
     Hess
    0.79
    しかし
    0.79
    PAIGN
    0.79
    genesis
    0.78
     ^
    0.78
    either
    0.78
    面色
    0.78
    Activations Density 0.002%

    No Known Activations