© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168763
    Prev
    Next
    INDEX
    Explanations

    cyber, malware, circuit

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

    control decisions and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    盻
    0.47
     Два
    0.46
     الظ
    0.44
    navigationLinks
    0.44
    rać
    0.43
    adrat
    0.43
    ,/*
    0.43
    childNodes
    0.42
    {
    0.41
    婼
    0.41
    POSITIVE LOGITS
     Cyber
    0.54
     malware
    0.50
     Circuit
    0.49
     circuito
    0.48
     persona
    0.47
     cyber
    0.47
     Malware
    0.47
     preset
    0.47
     circuit
    0.46
     Husky
    0.46
    Activations Density 0.000%

    No Known Activations