© 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. 10-GEMMASCOPE-RES-131K
    7. 10270
    Prev
    Next
    INDEX
    Explanations

    birthday celebrations

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

    The neuron fires on occurrences of the word “birthday.”

    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
     et
    -2.92
    泚
    -2.78
    〠
    -2.75
     donned
    -2.56
    垍
    -2.56
    </td>
    -2.50
     fourrure
    -2.47
    婼
    -2.42
    </h5>
    -2.36
    ViewInit
    -2.34
    POSITIVE LOGITS
     They
    2.72
    ti
    2.53
     绘画
    2.38
    ྅
    2.31
     Pense
    2.31
    F
    2.30
     foremost
    2.28
    姈
    2.27
     dwindling
    2.25
    岌
    2.25
    Activations Density 0.002%

    No Known Activations