© 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. 438
    Prev
    Next
    INDEX
    Explanations

    global locations

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

    The neuron fires most strongly on numeric tokens (digits, ordinals, and other number‐like expressions) 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
     MainAxisSize
    -0.88
    dei
    -0.83
     zumal
    -0.82
     для
    -0.81
    ご了承
    -0.79
    瞼
    -0.79
     Schaff
    -0.79
     будет
    -0.79
    APTER
    -0.79
    还得
    -0.78
    POSITIVE LOGITS
     Europe
    1.27
     Japan
    1.21
     worldwide
    1.18
     China
    1.18
     France
    1.16
     Germany
    1.09
     countries
    1.08
     Spain
    1.06
     elsewhere
    1.01
     abroad
    1.01
    Activations Density 0.119%

    No Known Activations