© 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. 50276
    Prev
    Next
    INDEX
    Explanations

    at, to, tops with numbers

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

    The neuron activates on numeric values and counts (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
     other
    -1.55
    mathrm
    -1.44
     many
    -1.30
    0
    -1.30
     each
    -1.25
     people
    -1.21
     specifically
    -1.21
    “…”
    -1.21
     quickly
    -1.20
     visibly
    -1.17
    POSITIVE LOGITS
     pourront
    1.35
     fidé
    1.32
     jouant
    1.23
     logiciels
    1.19
     arrivant
    1.14
    tieren
    1.14
     Mejor
    1.13
    
    1.13
     regardant
    1.13
    íng
    1.13
    Activations Density 0.137%

    No Known Activations