© 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. 39915
    Prev
    Next
    INDEX
    Explanations

    numbers and hyphens

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

    The neuron is triggered by numeric tokens (digits and numbers).

    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
     crecer
    -0.97
     dinámico
    -0.92
    тім
    -0.89
    ţii
    -0.87
    niche
    -0.87
    ító
    -0.85
    nba
    -0.85
    ります
    -0.85
     으로
    -0.84
     насеља
    -0.84
    POSITIVE LOGITS
     this
    1.02
    精华
    0.96
    Ⅲ
    0.94
     sappiamo
    0.93
     sometimes
    0.92
     насос
    0.90
     against
    0.89
     ফ
    0.87
    öglichkeiten
    0.87
     plano
    0.87
    Activations Density 0.001%

    No Known Activations