© 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. 34-GEMMASCOPE-RES-131K
    4. 2038
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and characters

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

    The neuron strongly responds to standalone digits and numeric tokens (i.e. 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_34/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
    になりたい
    -1.20
    んだよね
    -1.16
    を目指す
    -1.16
    のですね
    -1.13
    んですよね
    -1.13
    あー
    -1.13
    んでしょう
    -1.13
    様な
    -1.13
    あぁ
    -1.07
     zainteres
    -1.06
    POSITIVE LOGITS
    もしか
    1.21
    <bos>
    1.02
    參考文獻
    0.97
    紡
    0.94
    雜誌
    0.89
    を
    0.89
    醍
    0.88
     &_
    0.88
     hende
    0.88
     virgen
    0.87
    Activations Density 0.039%

    No Known Activations