© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17930
    Prev
    Next
    INDEX
    Explanations

    supervising activities and people

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

    leading or overseeing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     计算
    0.47
    estro
    0.46
     мони
    0.45
     lider
    0.45
    可视
    0.44
     inversa
    0.44
     ident
    0.44
    挽
    0.44
    ಗಳಿಗೆ
    0.43
     regul
    0.42
    POSITIVE LOGITS
     renovations
    0.44
     renovation
    0.43
     excavations
    0.43
    Paused
    0.42
     waiters
    0.42
    একটি
    0.41
    トライ
    0.41
     lagoon
    0.41
    一场
    0.40
     reforestation
    0.40
    Activations Density 0.040%

    No Known Activations