© 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. 34-GEMMASCOPE-RES-131K
    7. 63558
    Prev
    Next
    INDEX
    Explanations

    cybersecurity

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

    The neuron lights up on named entities and jargon from the cybersecurity domain—organization names, agencies, and specialized terms like “cyber,” “security,” “Directorate,” etc.

    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
    sequential
    -0.80
    контро
    -0.78
     sequentially
    -0.76
     menghindari
    -0.73
     Compliance
    -0.71
    LinkedHashMap
    -0.70
    Compliance
    -0.69
     Cancer
    -0.69
     włosów
    -0.69
    owanej
    -0.69
    POSITIVE LOGITS
     cyber
    1.83
     Cyber
    1.78
    Cyber
    1.73
     cybersecurity
    1.46
     Cybersecurity
    1.31
    cyber
    1.28
     Cy
    1.06
     cy
    1.02
     incidente
    0.98
     ciber
    0.98
    Activations Density 0.020%

    No Known Activations