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. 8181
    Prev
    Next
    INDEX
    Explanations

    religious and historical entities

    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
     ALL
    -0.99
     but
    -0.99
     may
    -0.98
     creating
    -0.97
     any
    -0.93
    يسة
    -0.93
     out
    -0.91
     or
    -0.89
    Any
    -0.89
     ONLY
    -0.89
    POSITIVE LOGITS
    pageX
    1.12
     GUIDELINES
    0.96
     ย
    0.95
     actuel
    0.95
    particularly
    0.95
     nouve
    0.94
    ıç
    0.94
    ✵
    0.93
     OFFERS
    0.92
    actually
    0.91
    Activations Density 0.010%

    No Known Activations