© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212003
    Prev
    Next
    INDEX
    Explanations

    drone lethal targeting kill

    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
    쐞
    0.46
    ুতি
    0.42
    砺
    0.40
     Polaribacter
    0.39
    oncesto
    0.39
    unication
    0.38
    шым
    0.38
     acond
    0.38
     러시아
    0.38
    凃
    0.38
    POSITIVE LOGITS
     lethal
    0.65
     drone
    0.58
     deadly
    0.56
     Drone
    0.54
     Obama
    0.52
     drones
    0.49
     killing
    0.48
     selecting
    0.48
    Obama
    0.47
     remotely
    0.46
    Activations Density 0.007%

    No Known Activations