© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5774
    Prev
    Next
    INDEX
    Explanations

    yields and rates

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

    The neuron is detecting standalone numeric tokens (i.e. numbers) 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
     ন্যাশনাল
    0.68
    urgeon
    0.63
    ilizar
    0.62
    urah
    0.59
    ματο
    0.57
     抗
    0.57
     並
    0.56
    ils
    0.55
    फ
    0.55
    ustain
    0.55
    POSITIVE LOGITS
     bedste
    0.55
     hyvä
    0.53
    好的
    0.51
     ওই
    0.51
     goede
    0.51
     поступа
    0.51
     acepta
    0.51
     incoming
    0.50
     ingres
    0.50
    であろう
    0.49
    Activations Density 0.000%

    No Known Activations