© 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. 60385
    Prev
    Next
    INDEX
    Explanations

    em after phaco

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

    The neuron is triggered by the character sequence “em” occurring anywhere inside a token.

    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
     After
    -3.52
     Not
    -3.27
     \
    -3.16
     (
    -3.05
     In
    -2.97
    ).
    -2.94
     “
    -2.89
    .”
    -2.88
    ’
    -2.78
     {
    -2.56
    POSITIVE LOGITS
    儇
    3.36
    谖
    3.23
     baumwolle
    3.19
     ܙ
    3.14
    퐿
    3.03
    謦
    2.98
    derdag
    2.97
    姽
    2.95
     Giappone
    2.94
    ቬ
    2.94
    Activations Density 0.026%

    No Known Activations