© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 84615
    Prev
    Next
    INDEX
    Explanations

    malware and viruses

    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
     situational
    0.42
     fortified
    0.42
     referrals
    0.42
     auditions
    0.41
     bastion
    0.41
    erals
    0.40
    🪜
    0.39
     лёг
    0.39
     fortification
    0.39
    ጬ
    0.38
    POSITIVE LOGITS
     virus
    1.14
     viruses
    1.12
     Viruses
    1.10
     malware
    1.09
     Virus
    1.03
    virus
    1.03
     vírus
    1.01
    病毒
    0.99
    Virus
    0.99
     ভাইরাস
    0.93
    Activations Density 0.095%

    No Known Activations