© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13663
    Prev
    Next
    INDEX
    Explanations

    code file paths

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

    The neuron strongly activates on standalone numeric tokens (digits or numbers) in code diff and file header contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    they
    -1.74
     to
    -1.52
     龙
    -1.49
    鶿
    -1.48
    ܆
    -1.35
    あとは
    -1.34
     bienvenue
    -1.28
     ressemb
    -1.27
     kus
    -1.25
    ︷
    -1.25
    POSITIVE LOGITS
     Zähne
    1.18
     Перейти
    1.16
    hilterra
    1.11
     mittleren
    1.10
    Dicas
    1.09
    ależ
    1.07
     monasterio
    1.07
     with
    1.07
     Mitteln
    1.05
     Москва
    1.04
    Activations Density 0.005%

    No Known Activations