© 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. 115932
    Prev
    Next
    INDEX
    Explanations

    artist residency programs

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

    This neuron fires on numeric tokens and the punctuation that typically appears around them—e.g. digits in dates, edition numbers, and URLs.

    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
    大军
    -1.02
    门店
    -0.97
     серебри
    -0.90
     modern
    -0.89
    udian
    -0.88
     Movie
    -0.88
    THISDAY
    -0.87
     оли
    -0.87
    ků
    -0.86
     Leader
    -0.86
    POSITIVE LOGITS
     artists
    1.66
     curator
    1.34
     artist
    1.25
    Artists
    1.22
     Artists
    1.19
    artist
    1.15
    artists
    1.15
     gallery
    1.12
     artistas
    1.10
     bílé
    1.10
    Activations Density 0.091%

    No Known Activations