© 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. 65854
    Prev
    Next
    INDEX
    Explanations

    completion or halting of activities

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

    The neuron fires most strongly on non‐word tokens—especially numbers and end-of-sentence punctuation (e.g. standalone years, digits, and “.”).

    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
     géographie
    -1.00
    ẫ
    -0.97
     schnellen
    -0.85
    punten
    -0.85
    ınızı
    -0.85
    agliari
    -0.83
     many
    -0.83
    ណ
    -0.81
     управля
    -0.81
     многих
    -0.79
    POSITIVE LOGITS
     proceedings
    1.74
     execution
    1.58
     hostilities
    1.55
     construction
    1.51
     production
    1.50
     operations
    1.44
     work
    1.41
     the
    1.40
     festivities
    1.36
    operations
    1.28
    Activations Density 0.172%

    No Known Activations