© 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. 70127
    Prev
    Next
    INDEX
    Explanations

    artists and people

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

    The neuron is a detector for numeric tokens and related numeric expressions (e.g. years, dates, fiscal quarters, share prices, version 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_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
    습니다
    -0.79
     teste
    -0.76
     dabei
    -0.75
    であるが
    -0.73
     سپس
    -0.69
     其
    -0.69
     δια
    -0.68
    赐
    -0.68
     terse
    -0.68
    ocused
    -0.68
    POSITIVE LOGITS
     భూ
    0.75
    笏
    0.75
     industrious
    0.75
     麗
    0.74
    的話
    0.74
     dialysis
    0.73
     somehow
    0.73
     hoppas
    0.70
    Zam
    0.69
    Hasil
    0.69
    Activations Density 0.210%

    No Known Activations