© 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. 36516
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

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

    the presence of numerals or digit sequences 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_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
     worldwide
    -1.29
    不愿
    -1.26
    stylers
    -1.25
    ellate
    -1.23
     começaram
    -1.22
     fizeram
    -1.19
     Germany
    -1.19
     nadru
    -1.18
     seçenek
    -1.16
     configurações
    -1.15
    POSITIVE LOGITS
     it
    1.45
     residents
    1.23
     community
    1.20
     on
    1.18
     our
    1.17
     It
    1.12
     Community
    1.04
     people
    1.02
     this
    1.02
    It
    1.01
    Activations Density 0.094%

    No Known Activations