© 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. 104317
    Prev
    Next
    INDEX
    Explanations

    URLs, currency, dates

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

    The neuron activates on numeric tokens—especially decimal or floating‐point 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_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
    urgo
    -0.96
    چار
    -0.91
     dévo
    -0.91
     său
    -0.86
    εύ
    -0.86
    アンス
    -0.85
    kész
    -0.85
    Αν
    -0.85
     noastră
    -0.84
    ～♪
    -0.84
    POSITIVE LOGITS
     aforementioned
    1.22
     also
    1.10
     myös
    1.02
     additional
    1.01
     thua
    0.91
    。
    0.91
     these
    0.90
     different
    0.90
    ;
    0.88
    Derp
    0.86
    Activations Density 0.124%

    No Known Activations