© 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. 11010
    Prev
    Next
    INDEX
    Explanations

    communication : plans or definitions

    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
     сі
    0.42
    aisu
    0.41
     comentário
    0.41
    kubernetes
    0.40
    enn
    0.39
     proposés
    0.39
    owości
    0.39
    仗
    0.38
     tinkering
    0.38
    heimer
    0.38
    POSITIVE LOGITS
     Communication
    0.93
    Communication
    0.91
     communication
    0.88
     коммуника
    0.82
     communications
    0.81
     Communications
    0.77
     comunicación
    0.75
    Communications
    0.75
     kommun
    0.74
     comunicação
    0.73
    Activations Density 0.016%

    No Known Activations