© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93299
    Prev
    Next
    INDEX
    Explanations

    parenthetical clauses and interjections

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

    The neuron fires on standalone numerical tokens (digit sequences), detecting numbers wherever they appear 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_22/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
     throughout
    -1.06
     which
    -1.03
     sowohl
    -1.01
    ELISA
    -0.96
     with
    -0.96
     vélos
    -0.93
    Anglo
    -0.93
     through
    -0.91
     усі
    -0.90
     Spare
    -0.89
    POSITIVE LOGITS
     başladı
    1.26
    También
    1.21
     նաև
    1.20
    Ausstattung
    1.13
     tekno
    1.13
     samti
    1.12
    if
    1.12
    message
    1.11
     utilisez
    1.09
    事も
    1.09
    Activations Density 0.029%

    No Known Activations