© 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. 65996
    Prev
    Next
    INDEX
    Explanations

    code, configuration, and identifiers

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

    This neuron activates on numeric literals or version‐style numbers (i.e. tokens consisting purely of digits).

    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
    وح
    -0.78
    Abril
    -0.77
    amerikan
    -0.77
    Wade
    -0.72
     動画
    -0.71
     हों
    -0.69
    Mathias
    -0.69
    לע
    -0.69
     waffle
    -0.67
    appel
    -0.66
    POSITIVE LOGITS
    cra
    0.77
    ldb
    0.75
    ⲟ
    0.73
    졍
    0.72
     dor
    0.72
    不由
    0.71
     wirkt
    0.71
    rimônio
    0.70
     zeigt
    0.69
     eer
    0.68
    Activations Density 0.915%

    No Known Activations