© 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. 107818
    Prev
    Next
    INDEX
    Explanations

    title

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

    The neuron strongly activates on numeric tokens (digits or 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
     OMITBAD
    -0.77
    껄
    -0.75
     美術
    -0.75
     Fiske
    -0.71
    нер
    -0.71
     profi
    -0.71
     daarbij
    -0.69
    ügen
    -0.69
    üge
    -0.69
     discogs
    -0.69
    POSITIVE LOGITS
     title
    8.00
    title
    6.28
     Title
    5.84
     titles
    5.81
    Title
    5.78
     título
    5.38
    TITLE
    5.19
     TITLE
    5.09
    タイトル
    4.75
    标题
    4.66
    Activations Density 0.231%

    No Known Activations