© 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. 12887
    Prev
    Next
    INDEX
    Explanations

    TS timestamp typescript

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

    The neuron strongly activates on short all‐caps letter sequences (acronyms or uppercase codes).

    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
    ندہ
    0.53
    urne
    0.52
     powers
    0.50
    ENTIAL
    0.50
     अनंत
    0.50
    marginLeft
    0.48
    ্টন
    0.48
    ჩ
    0.48
    ранже
    0.48
    
    0.48
    POSITIVE LOGITS
     تس
    0.68
     ts
    0.67
     TS
    0.65
     Цу
    0.60
    تس
    0.60
     التس
    0.59
     TSP
    0.58
     TSI
    0.57
     Tsar
    0.56
     Ts
    0.56
    Activations Density 0.111%

    No Known Activations