© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7779
    Prev
    Next
    INDEX
    Explanations

    equilibrium binding and states

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

    the word "equilibrium" and related terms in scientific contexts.

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

    The neuron activates on mentions of the term “equilibrium,” particularly in scientific or technical contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -2.02
     serán
    -1.56
     vollständige
    -1.55
     einfache
    -1.49
     dando
    -1.41
    buie
    -1.41
    -1.41
     ทำ
    -1.39
     startling
    -1.39
     tématu
    -1.37
    POSITIVE LOGITS
    Other
    1.63
     土産
    1.63
     other
    1.60
    　　(
    1.57
    𓆜
    1.51
    万物
    1.47
    replyreport
    1.45
    手绘
    1.44
    ꙳
    1.44
    )।
    1.43
    Activations Density 0.060%

    No Known Activations