© 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. 22-GEMMASCOPE-RES-131K
    4. 68339
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    The neuron activates specifically on numeric tokens (multi‐digit numbers and numeric constants) 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
     but
    -1.02
    动作
    -0.96
    pias
    -0.95
     Its
    -0.94
    velu
    -0.94
     Thailand
    -0.94
    MotionEvent
    -0.93
    5
    -0.92
    тов
    -0.91
    coeur
    -0.91
    POSITIVE LOGITS
     tenues
    1.07
     triom
    1.05
     vitale
    1.03
     incrí
    1.01
     malheure
    1.00
     initiale
    0.98
    綃
    0.98
     inaug
    0.96
    fazer
    0.96
    patrón
    0.96
    Activations Density 0.077%

    No Known Activations