© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47734
    Prev
    Next
    INDEX
    Explanations

    robots and robots taking

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

    mentions of robots, robot model names, or detailed robot-related descriptions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     задержа
    0.44
    mysqli
    0.44
    INTERVAL
    0.43
     RARRAY
    0.43
    alink
    0.42
     نثر
    0.42
    𝓪
    0.42
    產生
    0.42
    йда
    0.41
    ังหวัด
    0.41
    POSITIVE LOGITS
     robot
    1.59
     robots
    1.48
     robotic
    1.39
    机器人
    1.34
    Robot
    1.34
     Robot
    1.32
     robotics
    1.27
     Robots
    1.27
     Robotic
    1.22
     Robotics
    1.18
    Activations Density 0.212%

    No Known Activations