© 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. 22-GEMMASCOPE-RES-131K
    4. 12626
    Prev
    Next
    INDEX
    Explanations

    equilibrium shape, state, binding

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

    The neuron detects the word "equilibrium" in scientific and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly responds to occurrences of the word “equilibrium.”

    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
    1
    -3.03
     stalwart
    -3.00
    5
    -2.97
     insanely
    -2.97
     pivotal
    -2.84
     quintessential
    -2.84
     alcune
    -2.83
     tumultuous
    -2.81
     dismal
    -2.72
     delightfully
    -2.72
    POSITIVE LOGITS
    籐
    2.88
    ſelves
    2.61
     土産
    2.42
     apto
    2.33
     embodies
    2.25
    ൎ
    2.23
    逡
    2.19
    𓆜
    2.14
    زيل
    2.13
    ၅
    2.11
    Activations Density 0.008%

    No Known Activations