© 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. 23504
    Prev
    Next
    INDEX
    Explanations

    standalone and independent

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

    This neuron detects occurrences of the word “standalone” (or “stand-alone”), whether hyphenated or not (including XML standalone attributes).

    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
     امن
    -0.79
    xiao
    -0.78
    simult
    -0.73
    escent
    -0.73
     személy
    -0.72
    зил
    -0.72
    同一个
    -0.71
    oltre
    -0.70
     ソフト
    -0.69
    ajú
    -0.69
    POSITIVE LOGITS
     standalone
    5.84
    standalone
    4.84
    Standalone
    4.31
     stand
    3.89
     freestanding
    3.45
     Stand
    3.17
    独立
    3.13
     independent
    2.86
     самостоя
    2.83
     STAND
    2.80
    Activations Density 0.202%

    No Known Activations