© 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. 76191
    Prev
    Next
    INDEX
    Explanations

    change or modification

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

    The neuron detects words that denote making a change or modification (e.g., adapt, modify, change, amend, revise).

    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
     aproximativ
    -1.22
     aici
    -1.15
     немає
    -1.09
     diferite
    -1.09
     greu
    -1.07
     asemenea
    -1.07
     înal
    -1.02
     acestea
    -1.01
    likace
    -1.01
     разные
    -1.01
    POSITIVE LOGITS
     the
    2.59
     some
    1.99
     or
    1.95
     how
    1.89
     certains
    1.70
     to
    1.67
     برخی
    1.63
    某些
    1.61
     algunos
    1.48
     algumas
    1.44
    Activations Density 0.092%

    No Known Activations