© 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. 33403
    Prev
    Next
    INDEX
    Explanations

    ages and years following commas

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

    The neuron activates on numeric tokens (e.g. ages, measurements, counts, dates)—in other words, it finds numbers.

    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
    :
    -1.03
    ふと
    -0.98
     étant
    -0.97
     |]
    -0.95
     where
    -0.93
     reúne
    -0.91
     
    -0.91
    づくり
    -0.91
    様々
    -0.90
    をご覧
    -0.90
    POSITIVE LOGITS
     employee
    1.19
    ַּ
    1.14
     Hauses
    1.12
    翻攝
    1.09
     аккура
    1.06
    ִּ
    1.02
     wuß
    1.02
     almond
    1.02
     army
    1.02
     його
    1.01
    Activations Density 0.020%

    No Known Activations