© 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. 130810
    Prev
    Next
    INDEX
    Explanations

    The neuron chiefly activates on numeric tokens—digits and version‐style numbers embedded in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    introduces questions or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     their
    -1.77
     ее
    -1.16
     its
    -1.16
     soyez
    -1.13
    سد
    -1.11
     centavos
    -1.09
    子さん
    -1.09
     difficult
    -1.08
     її
    -1.08
     almost
    -1.05
    POSITIVE LOGITS
    tells
    1.39
     ロゴ
    1.38
     culoare
    1.34
     コレクション
    1.23
     étoient
    1.12
    といった
    1.09
     ラウンド
    1.09
    萼
    1.05
    chose
    1.05
     WER
    1.03
    Activations Density 0.001%

    No Known Activations