© 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. 55766
    Prev
    Next
    INDEX
    Explanations

    cyber security, crime, and intelligence

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

    The neuron fires on occurrences of “cyber” (including “Cyber,” “cyber-” compounds, and related high-frequency “cyber” tokens).

    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
     ANN
    -0.94
     minibar
    -0.93
    sapp
    -0.79
     whol
    -0.76
     ann
    -0.76
     blueberry
    -0.75
    如何在
    -0.74
    LETS
    -0.73
    chuga
    -0.72
    एम
    -0.71
    POSITIVE LOGITS
    attack
    1.37
    netic
    1.14
    attacks
    1.08
    crime
    1.02
    空間
    1.01
    SPACE
    0.98
     security
    0.98
    idoo
    0.97
     attacks
    0.97
    attaque
    0.96
    Activations Density 0.005%

    No Known Activations