© 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. 47940
    Prev
    Next
    INDEX
    Explanations

    bipolar junction transistor

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

    The neuron primarily responds to standalone numeric tokens (e.g. years, counts, dates) and document section headers.

    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
    าท
    -0.76
     Carlo
    -0.74
    isNotNull
    -0.67
    muchas
    -0.67
    护士
    -0.66
    mari
    -0.65
     arriva
    -0.65
     biru
    -0.65
    înd
    -0.63
    usap
    -0.63
    POSITIVE LOGITS
    इ
    0.73
     optimizer
    0.72
    یکی
    0.69
     Taunton
    0.69
     orphanage
    0.69
    剂
    0.68
    長の
    0.68
     Kabir
    0.67
     credibility
    0.65
    บ้าน
    0.65
    Activations Density 0.054%

    No Known Activations