© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15337
    Prev
    Next
    INDEX
    Explanations

    easy, simple, basic

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

    The neuron is detecting numeric tokens (digits and numbers, including decimals).

    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_24_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
     不能
    0.72
     metastable
    0.66
     DISTRICT
    0.66
    试图
    0.66
     Attempts
    0.66
     пыта
    0.64
     Persistence
    0.63
    坆
    0.62
     premature
    0.62
     緊急
    0.62
    POSITIVE LOGITS
    只需
    1.77
     easy
    1.73
    easy
    1.66
    簡単
    1.59
    只需要
    1.58
     간단
    1.54
    很简单
    1.51
     fácil
    1.45
     EASY
    1.44
    簡単な
    1.44
    Activations Density 0.833%

    No Known Activations