© 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. 34-GEMMASCOPE-RES-131K
    7. 12051
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities followed by common words

    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
    ことです
    -1.20
     conocidos
    -1.18
    了很多
    -1.02
     deft
    -1.01
     précé
    -1.01
     sellado
    -0.98
     cantidades
    -0.98
    が見える
    -0.98
     ihre
    -0.97
     исполь
    -0.97
    POSITIVE LOGITS
     ones
    2.31
     that
    2.19
     which
    1.59
     in
    1.43
     deles
    1.41
     for
    1.37
    Ones
    1.35
     throughout
    1.31
     from
    1.24
     others
    1.21
    Activations Density 0.161%

    No Known Activations