© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84370
    Prev
    Next
    INDEX
    Explanations

    words starting with "cons"

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

    The neuron strongly activates on tokens beginning with the character sequence “cons.”

    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
    ilty
    -0.88
    Barre
    -0.83
    鉛筆
    -0.81
    がありますが
    -0.79
     Barre
    -0.79
    economy
    -0.74
     Morrison
    -0.74
    motorola
    -0.73
     Padre
    -0.71
     Prophe
    -0.70
    POSITIVE LOGITS
    cons
    1.52
    Cons
    1.42
    Kons
    1.39
     Cons
    1.37
     kons
    1.28
     Kons
    1.27
     cons
    1.19
     consac
    1.07
     conspicuous
    1.06
    kons
    1.05
    Activations Density 0.017%

    No Known Activations