© 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. 22-GEMMASCOPE-RES-131K
    7. 14756
    Prev
    Next
    INDEX
    Explanations

    code, data structures, and numbers

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

    The neuron fires on numeric literal tokens (numbers) 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
    อื่น
    -1.02
    ԁ
    -0.95
    wanne
    -0.90
    ッチン
    -0.88
     koul
    -0.86
     巾
    -0.85
     dibujos
    -0.85
     historie
    -0.84
    ᵉ
    -0.84
     tutti
    -0.83
    POSITIVE LOGITS
     further
    0.91
     superiors
    0.86
     nemat
    0.84
     特徴
    0.83
    ętr
    0.83
     району
    0.81
    Desta
    0.79
     magi
    0.78
     fub
    0.77
     Intermediate
    0.77
    Activations Density 0.008%

    No Known Activations