© 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. 92206
    Prev
    Next
    INDEX
    Explanations

    " instructions for"

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

    The neuron fires on explicit instruction cues—words like “instructions,” related action verbs (e.g. “disable,” “set,” “out”), and accompanying links or numbered steps—that signal how-to or directive content.

    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
     за
    -0.88
     además
    -0.82
    ো
    -0.73
     contested
    -0.73
     sto
    -0.72
    ↵↵↵
    -0.71
    治愈
    -0.70
    дли
    -0.69
     Houses
    -0.69
    ണ്
    -0.69
    POSITIVE LOGITS
    kilometer
    0.85
    vées
    0.81
     droite
    0.81
    illées
    0.81
    ρης
    0.80
    饬
    0.79
     Kompon
    0.77
     popping
    0.77
     sjuk
    0.76
     Camargo
    0.76
    Activations Density 0.025%

    No Known Activations