© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12421
    Prev
    Next
    INDEX
    Explanations

    proper nouns and capitalized beginnings

    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_22/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
    <eos>
    -1.40
    These
    -1.39
    這些
    -1.33
    Many
    -1.23
    There
    -1.20
     these
    -1.19
    这些
    -1.18
     and
    -1.16
    Once
    -1.16
     so
    -1.14
    POSITIVE LOGITS
     después
    1.02
    enb
    1.00
     usando
    0.97
     Además
    0.96
     durer
    0.95
     avenir
    0.94
     музыки
    0.94
    狨
    0.92
     principalement
    0.92
    上がった
    0.91
    Activations Density 0.028%

    No Known Activations