© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38404
    Prev
    Next
    INDEX
    Explanations

    accomplish this

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

    The neuron detects occurrences of the word “accomplish” (and its inflected forms).

    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
     anderen
    -2.39
    鲀
    -2.28
     participaron
    -2.25
     nurture
    -2.23
     coloca
    -2.13
     decimos
    -2.13
     produkty
    -2.11
     impetus
    -2.05
     stalwart
    -2.05
     -
    -2.02
    POSITIVE LOGITS
    s
    2.63
    ↵
    2.56
    ୈ
    2.50
    g
    2.39
    ússia
    2.27
    劻
    2.17
    
    2.17
    ampiyon
    2.16
    n
    2.16
    
    2.11
    Activations Density 0.011%

    No Known Activations