© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103248
    Prev
    Next
    INDEX
    Explanations

    words ending in ational

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

    The neuron fires on words containing the suffix “ational,” i.e. words ending in “ational.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -3.30
    𝗟
    -3.00
     เมื่อ
    -2.89
    苌
    -2.73
     fazia
    -2.73
    xvii
    -2.72
    lancer
    -2.69
    嘰
    -2.66
     THIRD
    -2.63
    ☆☆☆☆
    -2.63
    POSITIVE LOGITS
    “
    3.89
    ism
    3.34
    7
    3.28
    X
    3.28
    1
    3.17
    _
    3.11
    ized
    3.09
    6
    3.08
    ist
    3.06
    3
    3.06
    Activations Density 0.061%

    No Known Activations