© 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. 14131
    Prev
    Next
    INDEX
    Explanations

    cybersecurity, signals, and intelligence

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

    The neuron fires on mentions of intelligence and signals‐intelligence organizations or terminology (e.g. agency names, SIGINT, Directorate, intelligence, NSA, ASD).

    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
     but
    -1.38
     obligado
    -1.28
    nhung
    -1.16
    一辈子
    -1.09
     bílé
    -1.09
    特有
    -1.09
    翾
    -1.09
    hướng
    -1.08
    んでいた
    -1.08
     guld
    -1.07
    POSITIVE LOGITS
    </h5>
    1.23
     появляется
    1.08
     Victim
    1.07
     they
    1.05
    frac
    1.05
    attack
    1.05
    ")
    1.04
    today
    1.03
    lês
    1.03
    array
    1.02
    Activations Density 0.060%

    No Known Activations