© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22022
    Prev
    Next
    INDEX
    Explanations

    malicious remote access and execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     психологи
    0.42
    遇到
    0.41
    istiques
    0.41
    楾
    0.41
    缀
    0.39
     lineColor
    0.38
     реак
    0.38
     saludable
    0.38
     cuttings
    0.38
     нужда
    0.37
    POSITIVE LOGITS
     malicious
    0.73
     backdoor
    0.65
    窃
    0.63
     steal
    0.62
     hijacking
    0.61
     takeover
    0.60
     maliciously
    0.59
     access
    0.57
     undetected
    0.57
     nefarious
    0.57
    Activations Density 0.056%

    No Known Activations