© 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. 102676
    Prev
    Next
    INDEX
    Explanations

    years, numbers, and dates

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

    This neuron flags apostrophe characters (’ or ') in text, marking possessives or contractions.

    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
    었
    -0.79
    épar
    -0.75
     网
    -0.75
    acie
    -0.74
     
    -0.72
    hees
    -0.71
    يس
    -0.71
    Been
    -0.71
    Inet
    -0.71
    بط
    -0.70
    POSITIVE LOGITS
     supaya
    0.78
    ворачи
    0.77
    atasi
    0.77
    キャ
    0.76
     numberOfRows
    0.75
     Dubois
    0.70
     Cabral
    0.69
     ק
    0.69
    stoffen
    0.68
     considerate
    0.68
    Activations Density 0.020%

    No Known Activations