© 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. 38008
    Prev
    Next
    INDEX
    Explanations

    AssemblyCompany, Platform, nodes

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

    The neuron activates on numeric literals (multi‐digit numbers) in code or XML.

    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
    めんな
    -0.76
    ItemCount
    -0.75
     Sheppard
    -0.75
    laquo
    -0.74
    nextProps
    -0.74
     interp
    -0.73
     Vad
    -0.73
    ého
    -0.73
    行った
    -0.73
     gone
    -0.71
    POSITIVE LOGITS
    alak
    0.82
     corruption
    0.77
    corruption
    0.77
     AssemblyCompany
    0.75
    verlust
    0.73
    indows
    0.71
     outerwear
    0.69
    stacked
    0.69
     selten
    0.69
    owski
    0.69
    Activations Density 0.028%

    No Known Activations