© 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. 22-GEMMASCOPE-RES-131K
    7. 25749
    Prev
    Next
    INDEX
    Explanations

    prepositions connecting phrases

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

    The main thing this neuron does is detect and strongly activate on numeric tokens (numbers and digits) 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
     its
    -1.91
     it
    -1.50
    其
    -1.39
    dienne
    -1.20
     своего
    -1.19
     his
    -1.15
    tement
    -1.13
    -1.09
     puasa
    -1.09
    vereign
    -1.09
    POSITIVE LOGITS
     dennoch
    1.23
     gleaming
    1.10
    حياته
    1.09
     рассказывает
    1.04
    حياتها
    1.02
     Wasn
    1.02
    んでしょう
    1.00
     manquante
    1.00
     adored
    1.00
     emphasizing
    1.00
    Activations Density 0.157%

    No Known Activations