© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113790
    Prev
    Next
    INDEX
    Explanations

    AES encryption

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

    the acronym "AES" (Advanced Encryption Standard) in technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on any occurrence of the letter sequence “aes” (in any casing), e.g. the acronym AES or the substring aes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     However
    -3.67
     While
    -3.55
    м
    -3.06
     That
    -3.05
     Sometimes
    -3.03
     There
    -2.94
     Since
    -2.92
     Although
    -2.91
    ↵
    -2.88
     For
    -2.86
    POSITIVE LOGITS
    and
    2.80
    苳
    2.70
    蠲
    2.63
    䜣
    2.55
     Dinas
    2.52
    amazing
    2.48
    秾
    2.47
    趿
    2.44
     autres
    2.42
    𓁹
    2.41
    Activations Density 0.001%

    No Known Activations