© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 486
    Prev
    Next
    INDEX
    Explanations

    dates and ages

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

    The neuron is picking up on numeric tokens (dates, years, times, and other numbers) and related punctuation in article metadata.

    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
     devez
    -0.91
     coute
    -0.85
    vastatin
    -0.82
     soie
    -0.82
     loup
    -0.81
    still
    -0.81
     moule
    -0.79
     allez
    -0.78
     privil
    -0.77
    TIMESTAMP
    -0.77
    POSITIVE LOGITS
     city
    1.02
    Reporter
    0.92
    leqslant
    0.91
     rematch
    0.91
    Insp
    0.90
     instead
    0.90
     “(
    0.88
    
    0.85
    Herald
    0.85
    研究院
    0.84
    Activations Density 0.033%

    No Known Activations