© 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. 73601
    Prev
    Next
    INDEX
    Explanations

    words ending in le

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

    This neuron detects words ending with the “-le” suffix.

    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
     decisão
    -0.96
    regel
    -0.92
    ster
    -0.89
    renewal
    -0.88
     radicals
    -0.87
     indústria
    -0.85
    으로
    -0.84
    yolo
    -0.83
    란
    -0.81
     Battles
    -0.81
    POSITIVE LOGITS
    icious
    1.52
    mania
    1.19
    ttes
    1.05
    butt
    0.97
    侂
    0.95
    berry
    0.91
    thorpe
    0.89
    baum
    0.89
    ized
    0.88
    ton
    0.83
    Activations Density 0.047%

    No Known Activations