© 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. 22-GEMMASCOPE-RES-131K
    7. 129588
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized in detecting numeric tokens (numbers and numeric constants) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code snippets with variables OR mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    鹮
    -1.55
    ’
    -1.36
    ’，
    -1.34
     aggiun
    -1.18
     ktore
    -1.17
    赑
    -1.13
    =“
    -1.13
    desertcart
    -1.13
     aspects
    -1.12
    のが
    -1.12
    POSITIVE LOGITS
    閦
    1.27
    sometimes
    1.20
    day
    1.11
    ⚋
    1.09
    垍
    1.08
    ࿚
    1.07
    oiden
    1.06
    x
    1.06
    sq
    1.03
    ISION
    1.03
    Activations Density 0.549%

    No Known Activations