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. 68
    Prev
    Next
    INDEX
    Explanations

    phone calls into high-quality video calls

    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
     but
    -1.02
     sehr
    -0.93
    还有一个
    -0.90
     although
    -0.90
     Many
    -0.85
    这件事情
    -0.83
    立派
    -0.83
     очень
    -0.83
    oferta
    -0.83
     bzw
    -0.82
    POSITIVE LOGITS
     your
    1.35
    ___________
    1.31
    ____________
    1.22
    *</
    1.16
    *"
    1.11
    ✱
    1.10
     ENTERTAINMENT
    1.10
    ¹
    1.09
    *",
    1.08
    
    1.08
    Activations Density 0.061%

    No Known Activations