© 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. 8713
    Prev
    Next
    INDEX
    Explanations

    Langley, abatement, modernization, Abbot, appellants, sourceforge

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

    This neuron activates on unusually long, multi‐syllable words.

    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
    慙
    -2.77
    悒
    -2.66
     แต่
    -2.66
    ჻
    -2.53
    LEncoder
    -2.53
     いた
    -2.50
    憷
    -2.50
    擧
    -2.50
    ſelves
    -2.48
     raiſ
    -2.48
    POSITIVE LOGITS
    ↵
    3.42
    {
    3.09
     =
    2.66
    ?
    2.50
     You
    2.44
     terwijl
    2.39
    1
    2.33
    なりに
    2.28
    8
    2.27
    ir
    2.20
    Activations Density 0.007%

    No Known Activations