© 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. 25539
    Prev
    Next
    INDEX
    Explanations

    student societies and campus events

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

    The neuron activates on tokens that are capitalized or uppercase—i.e. proper names, titles, headings, and other Title-Case or ALL-CAP words.

    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
     ترا
    -0.78
    KeyPressed
    -0.73
     Hotels
    -0.73
     اش
    -0.72
    zenio
    -0.70
     Sent
    -0.69
    同事
    -0.69
    LAHOMA
    -0.69
    iu
    -0.68
    CHAPTER
    -0.68
    POSITIVE LOGITS
     societies
    1.41
     fresher
    1.38
     RAG
    1.19
     Societies
    1.13
     campus
    1.05
     society
    1.05
     student
    1.05
    campus
    1.01
     Fres
    1.01
    student
    1.01
    Activations Density 0.018%

    No Known Activations