© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116720
    Prev
    Next
    INDEX
    Explanations

    Leisure, lease, Leeds, LEED

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

    This neuron activates on words beginning with the letter sequence “Le” (e.g. Leeds, Lepton, Leisure, Leased, Leasing).

    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
    ี่ยม
    -1.26
    连连
    -1.17
     Monats
    -1.16
     loosely
    -1.13
    v
    -1.09
     лампа
    -1.05
     货
    -1.05
    ᱹ
    -1.05
     likelihood
    -1.03
    Ciudad
    -1.02
    POSITIVE LOGITS
    心底
    1.23
     Ле
    1.20
    さんも
    1.16
    arrol
    1.16
    ?'
    1.12
    缔
    1.09
     entera
    1.08
    凪
    1.06
    ίες
    1.06
    iting
    1.06
    Activations Density 0.039%

    No Known Activations