© 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. 76496
    Prev
    Next
    INDEX
    Explanations

    security keys and encryption

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

    The neuron activates on capitalized technical identifiers and component names—especially API, driver, core, acronyms, and other module names—in code comments or documentation.

    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
     técnicos
    -0.84
    avajillas
    -0.84
    Optimize
    -0.84
    Ⱥ
    -0.82
    وسف
    -0.80
    irten
    -0.79
    幂
    -0.78
    Matty
    -0.77
     Obtén
    -0.77
     mène
    -0.77
    POSITIVE LOGITS
     secure
    1.45
     Secure
    1.30
     trustworthiness
    1.28
    Secure
    1.25
     chip
    1.21
     hardware
    1.19
     protect
    1.19
     trusted
    1.18
     protection
    1.13
     protected
    1.11
    Activations Density 0.047%

    No Known Activations