© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99878
    Prev
    Next
    INDEX
    Explanations

    microwaves and warfare

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

    This neuron responds to occurrences of the uppercase bigram “MW” (as used in acronyms like “MW2013,” “MWCNT,” or “Mobile World Congress”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TRAN
    -0.72
     Préférences
    -0.72
     numbers
    -0.71
    NSIndexPath
    -0.71
     bà
    -0.71
    вый
    -0.69
     звезда
    -0.69
    Ệ
    -0.68
     thuật
    -0.67
     numeri
    -0.67
    POSITIVE LOGITS
     mw
    0.93
     Mw
    0.84
    mw
    0.81
    Jogo
    0.81
     chứa
    0.76
     shouted
    0.73
    štu
    0.72
    จะมี
    0.72
     MW
    0.71
    reasonably
    0.71
    Activations Density 0.023%

    No Known Activations