© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37940
    Prev
    Next
    INDEX
    Explanations

    quantum simulation algorithms

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

    The neuron activates strongly on numeric tokens, mathematical notation, code‐like imports/paths, and other highly technical or scientific terms.

    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
     Schuh
    -0.83
    requestData
    -0.80
     чому
    -0.79
     sank
    -0.78
     triplet
    -0.76
    ETRIC
    -0.75
    riebe
    -0.75
     undertook
    -0.73
     ~(
    -0.73
     מוס
    -0.73
    POSITIVE LOGITS
     DMR
    0.89
     circuit
    0.85
     Productive
    0.85
     simulating
    0.85
     simula
    0.82
    MPS
    0.82
     MPS
    0.81
    이다
    0.79
    mera
    0.78
     Vari
    0.78
    Activations Density 0.086%

    No Known Activations