© 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. 127306
    Prev
    Next
    INDEX
    Explanations

    backpacks and carrying bags

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

    backpacks and bags

    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
     cavité
    0.50
     tabletop
    0.48
     screwdriver
    0.47
    插入
    0.46
     candlestick
    0.46
     cleanser
    0.46
    盒
    0.44
     nắm
    0.44
     tweezers
    0.43
     socket
    0.43
    POSITIVE LOGITS
    🎒
    0.68
     mochila
    0.64
     ショルダーバッグ
    0.59
    backpack
    0.57
     backpacks
    0.54
    肩
    0.54
     scolaire
    0.51
     リュック
    0.51
     Backpack
    0.50
    scholar
    0.50
    Activations Density 0.080%

    No Known Activations