© 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. 22-GEMMASCOPE-RES-131K
    4. 84409
    Prev
    Next
    INDEX
    Explanations

    from X to Y

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

    The neuron activates on numeric measurement tokens—especially large multi‐digit values indicating a change or magnitude in scientific or technical contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    unlike
    -1.32
     OGSÅ
    -1.09
    férés
    -1.09
    Keine
    -1.05
     inapropiados
    -1.05
    総評
    -1.05
    饜
    -1.05
    pedes
    -1.05
    ⌵
    -1.04
     unlike
    -1.02
    POSITIVE LOGITS
     innumerable
    1.11
     now
    1.09
     more
    1.05
    >
    
    1.04
     муки
    1.01
    ⦑
    1.01
    èbre
    1.00
    Amical
    1.00
     характеризу
    0.99
    erals
    0.98
    Activations Density 0.013%

    No Known Activations