© 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. 127672
    Prev
    Next
    INDEX
    Explanations

    the word moment

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

    The neuron strongly activates on occurrences of the word “moment.”

    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
     pezzo
    -2.81
    
    -2.69
    齪
    -2.67
     merav
    -2.66
    趿
    -2.59
     bicchiere
    -2.58
     ottimo
    -2.55
     evidenced
    -2.47
     aiuto
    -2.47
     utilizzo
    -2.45
    POSITIVE LOGITS
     "
    2.69
    ↵↵
    2.61
     Importantly
    2.58
    ?
    2.55
     «
    2.47
    题材
    2.42
    -
    2.38
     Some
    2.36
    …
    2.31
     ("
    2.28
    Activations Density 0.007%

    No Known Activations