© 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. 1635
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of refusing or being unwilling to perform (national) service, especially conscription.

    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
    ﻤ
    0.85
     Бра
    0.82
    о
    0.79
    ovaná
    0.79
    Amino
    0.79
    ῴ
    0.79
    ﻭ
    0.78
    Blockchain
    0.77
    ﻨ
    0.77
    N
    0.76
    POSITIVE LOGITS
     aforementioned
    1.10
     pesky
    1.05
     whim
    0.86
     trusty
    0.86
     dast
    0.85
     fue
    0.82
     fez
    0.82
     plek
    0.80
     burgeoning
    0.79
     paltry
    0.79
    Activations Density 0.867%

    No Known Activations