© 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. 22-GEMMASCOPE-RES-131K
    7. 40205
    Prev
    Next
    INDEX
    Explanations

    expressions and calculations

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

    The neuron specializes in spotting numeric constants (digits or numbers) in code and mathematical expressions.

    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
     that
    -1.48
     of
    -1.39
    ERÍA
    -1.05
    моло
    -1.01
     брюки
    -0.96
    етки
    -0.96
     ilyen
    -0.94
    ᾽
    -0.92
    СУ
    -0.92
    зад
    -0.91
    POSITIVE LOGITS
     positivo
    1.06
     gastron
    0.97
     salta
    0.95
    都需要
    0.95
     diverti
    0.95
     veículo
    0.94
     suscit
    0.94
    oczes
    0.93
    ございました
    0.93
    Rol
    0.93
    Activations Density 0.004%

    No Known Activations