© 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. 31-GEMMASCOPE-2-RES-65K
    7. 50293
    Prev
    Next
    INDEX
    Explanations

    potential for power dynamics

    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_31_width_65k_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
    ੩
    0.50
    交渉
    0.49
    𒁀
    0.49
     vendre
    0.48
     premio
    0.47
     médiocrement
    0.46
    ješ
    0.46
    쯜
    0.46
    💘
    0.46
    稒
    0.46
    POSITIVE LOGITS
     workplaces
    0.62
     onboarding
    0.61
     workspaces
    0.60
     researchers
    0.59
     users
    0.58
     robots
    0.57
     uptime
    0.57
     workloads
    0.57
     proactively
    0.56
     sensors
    0.55
    Activations Density 0.024%

    No Known Activations