© 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. 8313
    Prev
    Next
    INDEX
    Explanations

    waste, disposal, and recycling of gowns

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

    waste and recycling

    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
     தேர்வு
    0.49
     leçon
    0.45
    擢
    0.44
    剧情
    0.43
     outspoken
    0.42
     electroweak
    0.42
     hinsichtlich
    0.42
    辩
    0.42
     öğren
    0.42
     auteur
    0.42
    POSITIVE LOGITS
     waste
    1.18
    waste
    1.08
     disposal
    1.06
     Waste
    1.02
    Waste
    1.02
     WASTE
    0.97
     déchets
    0.96
     wastes
    0.95
     Disposal
    0.93
     recycling
    0.92
    Activations Density 0.247%

    No Known Activations