© 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. 75649
    Prev
    Next
    INDEX
    Explanations

    honorifics before names

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

    The neuron fires primarily on numeric tokens (dates, times, and other multi‐digit numbers) in the text.

    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
     Zelensky
    -1.09
     Buhari
    -0.95
     Putin
    -0.94
     Bolsonaro
    -0.92
     सिंह
    -0.89
     queste
    -0.88
    Singh
    -0.88
    俺
    -0.88
     Quận
    -0.86
    ipen
    -0.85
    POSITIVE LOGITS
     Mr
    4.53
     Ms
    3.44
    Mr
    3.08
    Ms
    2.45
     Mrs
    2.27
     Messrs
    2.17
     Dr
    1.88
     Miss
    1.74
     آقای
    1.55
    Mrs
    1.43
    Activations Density 0.034%

    No Known Activations