© 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. 34-GEMMASCOPE-RES-131K
    7. 63156
    Prev
    Next
    INDEX
    Explanations

    chain rule or reaction

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

    The main thing this neuron does is detect occurrences of the word “chain.”

    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
    ednesdays
    -0.91
    .
    -0.85
    стасия
    -0.85
    ﻃ
    -0.84
     equal
    -0.83
    unite
    -0.82
     sentimenti
    -0.81
    longed
    -0.79
     doo
    -0.79
    都要
    -0.78
    POSITIVE LOGITS
     Chain
    2.28
     chain
    2.06
     CHAIN
    1.82
    chain
    1.80
    Chain
    1.79
    CHAIN
    1.60
     chains
    1.55
     Chains
    1.54
     chained
    1.41
    Chains
    1.31
    Activations Density 0.012%

    No Known Activations