© 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. 10-GEMMASCOPE-RES-131K
    7. 84384
    Prev
    Next
    INDEX
    Explanations

    crown

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

    The neuron specifically fires on occurrences of the token “crown.”

    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
     Of
    -2.88
    
    -2.33
    してしまう
    -2.28
     you
    -2.27
     Also
    -2.22
    閦
    -2.20
    ではある
    -2.17
     said
    -2.14
    ть
    -2.11
    elerik
    -2.05
    POSITIVE LOGITS
     tetapi
    2.81
    ܆
    2.50
    们的
    2.36
    鸯
    2.34
    に
    2.34
     baumwolle
    2.33
    <i>
    2.33
    有
    2.31
    ла
    2.30
    اً
    2.28
    Activations Density 0.002%

    No Known Activations