© 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. 22-GEMMASCOPE-RES-131K
    4. 40131
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    The neuron is primarily triggered by numeric digits (numbers), especially those appearing in dates and timestamps.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     недавно
    -1.28
     spise
    -1.20
     aforementioned
    -1.12
    änderung
    -1.12
     communiquez
    -1.11
    Тел
    -1.11
     interessantes
    -1.09
     históricas
    -1.09
    Interestingly
    -1.08
     mencionado
    -1.07
    POSITIVE LOGITS
    MathML
    1.13
    })->
    1.09
    都被
    1.08
    精
    1.05
     включая
    1.03
    就在
    1.02
    1.01
    呼吸
    0.98
    }^{
    0.97
     położ
    0.95
    Activations Density 0.260%

    No Known Activations