© 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. 118341
    Prev
    Next
    INDEX
    Explanations

    thick

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

    The neuron responds strongly to the word “thick” (and its compounds or adjoining subword pieces).

    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
    トーン
    -0.88
     disassembled
    -0.84
     раск
    -0.84
    憶
    -0.84
    盒子
    -0.84
     незавер
    -0.83
    情报
    -0.82
     fiend
    -0.82
    евич
    -0.82
    koon
    -0.82
    POSITIVE LOGITS
     thick
    1.84
    Thick
    1.79
    thick
    1.60
     Thick
    1.53
     épais
    1.48
     thicker
    1.23
     två
    1.22
    eners
    1.16
     thickness
    1.16
     thickening
    1.15
    Activations Density 0.014%

    No Known Activations