© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9543
    Prev
    Next
    INDEX
    Explanations

    JSON structure keys

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

    The neuron activates on numeric tokens—especially multi‐digit and decimal numbers—highlighting numerical values in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     度
    0.55
     Debi
    0.53
    deselect
    0.53
     يق
    0.52
    ড়ান্ত
    0.52
    편집
    0.52
     بیچ
    0.51
     森
    0.51
     मुकाबला
    0.50
    XML
    0.48
    POSITIVE LOGITS
     message
    0.94
     data
    0.88
     Message
    0.81
    message
    0.78
     DATA
    0.77
     msg
    0.76
    メッセージ
    0.73
     messaggio
    0.71
     Data
    0.71
    data
    0.70
    Activations Density 0.004%

    No Known Activations