© 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. 11141
    Prev
    Next
    INDEX
    Explanations

    IEEE publications and standards

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

    The neuron is detecting occurrences of “IEEE” in bibliographic entries—i.e. references to IEEE journals or conferences.

    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
     Königreich
    0.71
     Bereiche
    0.68
    forcements
    0.66
    Ა
    0.66
     അങ്ങനെ
    0.63
    
    0.63
    법
    0.61
    Ꞌ
    0.61
    ศัพท์
    0.61
    ści
    0.60
    POSITIVE LOGITS
     witness
    0.63
     collider
    0.59
     crown
    0.58
     cut
    0.55
     lecture
    0.53
     attempt
    0.53
     giggle
    0.53
     comb
    0.52
     purple
    0.52
     stainless
    0.51
    Activations Density 0.003%

    No Known Activations