© 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. 115874
    Prev
    Next
    INDEX
    Explanations

    autocomplete and disabling it

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

    The neuron fires on instances of the word “autocomplete” (or “auto complete”), i.e. references to an autocomplete feature.

    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
    本土
    -0.85
    телям
    -0.84
    dbury
    -0.80
    still
    -0.79
     마
    -0.77
     Needle
    -0.75
     вещи
    -0.75
     kha
    -0.74
    rss
    -0.74
     Calf
    -0.71
    POSITIVE LOGITS
     off
    1.16
     OFF
    0.96
    off
    0.94
     collaborated
    0.90
    nope
    0.90
    些什么
    0.87
    OFF
    0.86
     auto
    0.84
     tingling
    0.82
    Off
    0.79
    Activations Density 0.005%

    No Known Activations