© 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. 98499
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

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

    The neuron activates primarily on numeric sequences (numbers or digit strings) 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
     it
    -1.37
    levis
    -1.18
    celona
    -1.17
    calips
    -1.16
     Coloque
    -1.06
    /',
    -1.05
    ✨:
    -1.03
    /",
    -1.03
    ;"><
    -1.02
    kapital
    -1.01
    POSITIVE LOGITS
    Приготовление
    1.19
    توضیحات
    1.16
    معرفی
    1.09
    مشخصات
    1.09
    Мы
    1.09
     metav
    1.06
    我們
    1.06
    einer
    1.05
    óstico
    1.03
    آیا
    1.02
    Activations Density 0.001%

    No Known Activations