© 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. 66340
    Prev
    Next
    INDEX
    Explanations

    company names and product brands

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

    The neuron selectively activates on numerical tokens and quantitative measurements (e.g. counts, units, years, page or figure 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
     ancienne
    -1.05
     marchés
    -0.98
     antiguos
    -0.93
     tromper
    -0.93
     ktore
    -0.92
     séjours
    -0.91
    UIFont
    -0.91
     délais
    -0.90
     calendriers
    -0.88
     achats
    -0.87
    POSITIVE LOGITS
     tremendously
    1.20
     greatly
    1.17
     considerably
    1.17
     substantially
    1.11
     seemingly
    1.07
     aptly
    1.05
     Insta
    1.05
     extraordinarily
    1.03
     considerable
    1.02
     overtly
    1.02
    Activations Density 0.260%

    No Known Activations