© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25987
    Prev
    Next
    INDEX
    Explanations

    Diffie-Hellman exchange and ECDH

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

    The neuron activates on cryptography jargon—terms like “key,” “secret,” “ECDH,” “ECC,” “DH,” and related algorithm names.

    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
    ksan
    -0.78
    dud
    -0.73
     aplicada
    -0.73
     Peace
    -0.71
    ettür
    -0.71
     aplicado
    -0.71
     Sher
    -0.70
     Michelin
    -0.68
     provved
    -0.68
     Ume
    -0.68
    POSITIVE LOGITS
     Diff
    1.17
    dh
    1.04
    DH
    1.01
     DH
    1.01
     dh
    0.91
    Diff
    0.90
     exchanged
    0.86
    diff
    0.80
     ephemeral
    0.79
     shared
    0.76
    Activations Density 0.201%

    No Known Activations