© 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. 14229
    Prev
    Next
    INDEX
    Explanations

    temporal kinetics

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

    This neuron responds to special code or markup tokens (e.g. angle brackets, backslashes, macro names) used in code/markup syntax.

    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
    \
    -2.02
    嗚
    -1.86
     comprimidos
    -1.82
     perplexing
    -1.80
     ostensibly
    -1.80
     With
    -1.80
     exquisitely
    -1.79
    琹
    -1.79
    你喜欢
    -1.77
     one
    -1.75
    POSITIVE LOGITS
    </strong>
    2.47
    .
    2.19
    five
    2.06
     .(
    2.05
    four
    1.95
     ij
    1.91
     nowy
    1.90
     crucial
    1.89
    six
    1.89
    啻
    1.87
    Activations Density 0.000%

    No Known Activations