© 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. 40336
    Prev
    Next
    INDEX
    Explanations

    academic, technical, and programming terms

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

    The neuron fires on standalone numeric tokens (i.e. sequences of 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
     Ceará
    -1.14
     oxigen
    -1.05
     plati
    -1.03
     vermelhas
    -1.03
    inine
    -1.02
     parto
    -1.01
     inverte
    -1.00
    بخ
    -0.99
     elog
    -0.99
     tipe
    -0.98
    POSITIVE LOGITS
    ia
    1.12
    了自己的
    1.06
    ike
    1.05
    了自己
    1.04
    ul
    1.03
    ica
    1.02
    5
    1.02
    了不少
    0.99
    4
    0.99
    想必
    0.97
    Activations Density 0.000%

    No Known Activations