© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75937
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     enticing
    -1.03
     innumerable
    -0.91
     endlessly
    -0.90
     psychotic
    -0.90
     oftentimes
    -0.88
     amidst
    -0.87
     two
    -0.86
     cerdas
    -0.86
    七月
    -0.86
    鏵
    -0.85
    POSITIVE LOGITS
     Zahlen
    0.96
     numbers
    0.93
     WIL
    0.92
     molte
    0.90
    scores
    0.90
     durante
    0.89
     primes
    0.89
     spectacular
    0.88
    了不少
    0.88
     že
    0.86
    Activations Density 0.022%

    No Known Activations