© 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. 58617
    Prev
    Next
    INDEX
    Explanations

    Niches, Nicodemus, Nicobar, Nicéphore, Nicotiana

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

    instances of "Niches" or variations of "Nic" particularly in website/domain contexts.

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

    This neuron fires on the repeated “Nic”/“hes” token pairs—i.e. when the document shows the word “Niches.”

    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
     savo
    -0.80
     Vorg
    -0.78
     Reflect
    -0.78
    頗
    -0.76
     Económica
    -0.76
     開始
    -0.76
    囉
    -0.75
    ֝
    -0.74
     quite
    -0.73
    途
    -0.73
    POSITIVE LOGITS
     Nic
    1.75
    Nic
    1.56
     nic
    1.40
    nic
    1.27
     NIC
    1.15
     Nich
    1.12
    Nice
    1.03
    ニコ
    0.98
     nich
    0.98
     Nicholls
    0.94
    Activations Density 0.015%

    No Known Activations