© 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. 103880
    Prev
    Next
    INDEX
    Explanations

    adding and mixing ingredients

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

    This neuron fires on the listing of components, quantities, or materials (e.g. “mix,” “add,” commas separating ingredients) typical of enumerations in technical/method sections.

    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
    ſo
    -0.96
    ølge
    -0.88
    🥈
    -0.84
     famí
    -0.83
    杷
    -0.81
    unately
    -0.80
     voies
    -0.79
    volts
    -0.79
    odor
    -0.78
    вёр
    -0.78
    POSITIVE LOGITS
     additives
    1.58
     water
    1.55
     additional
    1.53
     added
    1.33
     additions
    1.23
     varying
    1.13
     adding
    1.13
     zusätzlich
    1.11
     other
    1.09
    addi
    1.05
    Activations Density 0.128%

    No Known Activations