© 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. 14681
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

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

    The neuron fires strongly on numeric tokens (digits or numbers) appearing 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_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
    still
    -1.84
     он
    -1.70
    ”,
    -1.56
     ainda
    -1.54
    which
    -1.50
    ’,
    -1.47
    fsen
    -1.46
    ,’
    -1.41
     Which
    -1.39
     diarias
    -1.39
    POSITIVE LOGITS
     الأخرى
    1.39
     adverten
    1.36
     torba
    1.31
    一隻
    1.26
     ministra
    1.26
     玛
    1.23
    fpath
    1.23
     leſs
    1.23
    Rye
    1.22
    футболка
    1.20
    Activations Density 0.146%

    No Known Activations