© 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. 79553
    Prev
    Next
    INDEX
    Explanations

    Pique macha

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

    This neuron detects numeric expressions and hyphenated number patterns (e.g. scores like “4-0” or “five-wicket”) commonly found in sports reporting.

    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
    기를
    -0.82
      
    -0.82
     vola
    -0.80
     скан
    -0.80
     该
    -0.79
    mM
    -0.77
     основан
    -0.76
     Congresso
    -0.73
    elfde
    -0.71
    访
    -0.71
    POSITIVE LOGITS
    olique
    1.09
    initWithFrame
    1.05
     waardoor
    1.01
     Meningkatkan
    1.01
    ζει
    1.01
    nější
    1.00
    ッキ
    0.99
    вная
    0.99
    +"
    0.99
    ανα
    0.98
    Activations Density 0.005%

    No Known Activations