© 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. 59853
    Prev
    Next
    INDEX
    Explanations

    celebrity news and public figures

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

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

    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
    atically
    -0.99
     analis
    -0.87
     ett
    -0.87
    landers
    -0.86
    arounds
    -0.85
    THO
    -0.83
    bly
    -0.82
    地道
    -0.81
     ][
    -0.81
    areg
    -0.81
    POSITIVE LOGITS
     Grammy
    1.18
     singer
    1.15
     former
    1.02
     musician
    0.98
     star
    0.98
     entrepreneur
    0.96
     founder
    0.93
     award
    0.91
     ehemalige
    0.90
     American
    0.86
    Activations Density 0.028%

    No Known Activations