© 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. 12012
    Prev
    Next
    INDEX
    Explanations

    college student academic topics

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

    The neuron fires on tokens containing numbers or numeric identifiers (e.g. years, IDs, constants).

    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
     after
    -0.85
     Hür
    -0.79
    üyük
    -0.78
    越南
    -0.73
    ஏ
    -0.72
     when
    -0.71
     domestically
    -0.71
    𝖆
    -0.71
    玖
    -0.71
    affaires
    -0.71
    POSITIVE LOGITS
     department
    1.27
     batch
    1.23
     roll
    1.20
    hod
    1.16
     engineering
    1.14
     hostel
    1.11
     Roll
    1.09
    department
    1.08
    HOD
    1.06
     Batch
    1.05
    Activations Density 0.013%

    No Known Activations