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. 8208
    Prev
    Next
    INDEX
    Explanations

    military service branches

    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
     quilts
    -0.85
     Terkait
    -0.82
    IFORNIA
    -0.81
     masks
    -0.81
     toArray
    -0.77
    يط
    -0.77
     Técnica
    -0.77
    غرب
    -0.76
    maire
    -0.75
     licences
    -0.75
    POSITIVE LOGITS
     branches
    1.91
     branch
    1.85
     service
    1.77
    branch
    1.60
    service
    1.49
    branches
    1.49
     Service
    1.48
    Service
    1.44
     Branches
    1.43
     Branch
    1.42
    Activations Density 0.038%

    No Known Activations