© 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. 69773
    Prev
    Next
    INDEX
    Explanations

    celebrate events

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

    The neuron specifically activates on the word “celebrate” (and its close variants) in the text.

    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
     '
    -3.41
     we
    -2.94
     WHEN
    -2.83
     `
    -2.78
     es
    -2.69
     be
    -2.66
     OTHER
    -2.63
     необходимо
    -2.58
     ascertain
    -2.52
     \"
    -2.45
    POSITIVE LOGITS
     纹身
    3.14
     雞
    3.03
    唞
    3.02
    狁
    2.69
     chofe
    2.56
    𞤢
    2.55
    臯
    2.52
     fati
    2.48
    :”
    2.47
    筚
    2.47
    Activations Density 0.007%

    No Known Activations