© 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. 75348
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and expressions

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

    The neuron is specialized to detect numeric tokens (i.e. standalone 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_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
    ข้อมูล
    -1.26
     embalaje
    -1.25
    detek
    -1.23
     estampado
    -1.23
    anair
    -1.23
    érôme
    -1.23
     reciclado
    -1.23
    akaran
    -1.22
     иден
    -1.22
    nerability
    -1.21
    POSITIVE LOGITS
     now
    1.35
     for
    1.27
    on
    1.24
    z
    1.20
    la
    1.20
    _
    1.16
    ES
    1.16
    y
    1.15
    r
    1.13
    P
    1.13
    Activations Density 0.011%

    No Known Activations