© 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. 54436
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables

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

    The neuron spikes on numeric literal tokens (especially decimal or multi‐digit numbers) in mathematical expressions.

    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
    ${
    -1.02
    ğum
    -0.94
     вое
    -0.92
     Braun
    -0.90
    Ibid
    -0.89
    ⌊
    -0.89
    issent
    -0.88
    だろう
    -0.87
    edin
    -0.87
     rights
    -0.86
    POSITIVE LOGITS
     perplexing
    1.00
    After
    0.95
    jangkau
    0.94
    Several
    0.93
    Mejor
    0.92
    ماذا
    0.91
     other
    0.91
    ڼ
    0.89
     الآخر
    0.89
     proč
    0.88
    Activations Density 0.008%

    No Known Activations