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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32168
    Prev
    Next
    INDEX
    Explanations

    numbers and quantifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of numeric literals (i.e. tokens consisting of numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ѯ
    -0.87
     constantly
    -0.76
     Polisi
    -0.75
    tectable
    -0.75
    ᴮ
    -0.75
    ابراین
    -0.73
     demonic
    -0.72
     trato
    -0.72
     yana
    -0.71
     EFL
    -0.71
    POSITIVE LOGITS
     two
    1.06
     three
    0.96
    Tên
    0.88
     woorden
    0.83
     étage
    0.80
     comentarios
    0.80
    three
    0.77
     vijf
    0.77
    hre
    0.77
     két
    0.77
    Activations Density 0.000%

    No Known Activations