© 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. 2115
    Prev
    Next
    INDEX
    Explanations

    parliamentary legislative matters

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

    The neuron fires on numeric tokens—years, dates, counts, and other number strings 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
     kaum
    -0.79
     Sections
    -0.75
     Pohl
    -0.72
    する方法
    -0.72
     SUNDAY
    -0.70
    botanical
    -0.70
     aldehyde
    -0.68
    parade
    -0.68
    ザイン
    -0.68
     Council
    -0.67
    POSITIVE LOGITS
     étudié
    1.01
     estudio
    0.84
     Whigs
    0.80
     يقوم
    0.79
    amante
    0.77
     Commons
    0.77
    uteness
    0.77
    ยม
    0.77
     interpreters
    0.76
     circons
    0.75
    Activations Density 0.014%

    No Known Activations