© 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. 76587
    Prev
    Next
    INDEX
    Explanations

    malware virus scanning definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     swimmer
    -0.86
     fertility
    -0.76
     letra
    -0.75
     invokingState
    -0.75
     uninstall
    -0.73
    grove
    -0.73
    数据
    -0.72
    HttpException
    -0.71
     pain
    -0.71
    idencial
    -0.70
    POSITIVE LOGITS
     scanned
    1.32
     scan
    1.32
     scanning
    1.22
     suspicious
    1.20
     Scan
    1.12
     scanners
    1.11
    scanning
    1.09
    picious
    1.02
     verdicts
    1.02
    Scan
    0.97
    Activations Density 0.022%

    No Known Activations