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. 8236
    Prev
    Next
    INDEX
    Explanations

    arising from use

    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
    νονται
    -0.92
    Alzheimer
    -0.91
     tiennent
    -0.90
    cés
    -0.89
     oslo
    -0.88
    osť
    -0.87
     cultura
    -0.87
    そこは
    -0.86
    러나
    -0.85
     vagas
    -0.85
    POSITIVE LOGITS
     or
    1.56
     this
    1.33
     any
    1.13
     use
    1.05
     activities
    0.99
     arise
    0.99
     transactions
    0.98
     arises
    0.98
    การ
    0.98
     ANYTHING
    0.98
    Activations Density 0.016%

    No Known Activations