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. 8245
    Prev
    Next
    INDEX
    Explanations

    goals and numbers

    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
     thousands
    -0.91
     dono
    -0.88
    具体的な
    -0.86
    Hundreds
    -0.85
    群馬
    -0.85
    地说
    -0.83
     firms
    -0.83
     centuries
    -0.82
    mastered
    -0.79
    Thousands
    -0.79
    POSITIVE LOGITS
     nine
    0.93
    feng
    0.85
    nine
    0.84
     server
    0.83
     Rao
    0.81
    twelve
    0.81
     слу
    0.80
     Flora
    0.80
    Pacific
    0.79
    rack
    0.79
    Activations Density 0.017%

    No Known Activations