© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35806
    Prev
    Next
    INDEX
    Explanations

    names and dates

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

    This neuron detects numeric figures and percent expressions (e.g. percentages, counts, and other numerals).

    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
     so
    -1.00
    如今
    -0.97
     klimat
    -0.88
     subsequently
    -0.86
    niska
    -0.85
     kolor
    -0.83
    trusive
    -0.83
     then
    -0.83
     konkurs
    -0.82
     След
    -0.82
    POSITIVE LOGITS
     zuvor
    0.96
     vẫn
    0.87
     nachdem
    0.85
    paravant
    0.84
     last
    0.83
     wcześniej
    0.83
     cumplen
    0.83
     sebelumnya
    0.83
     yesterday
    0.82
    んじゃ
    0.82
    Activations Density 0.015%

    No Known Activations