© 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. 14755
    Prev
    Next
    INDEX
    Explanations

    bridal dress lace

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

    dresses, gowns, and attire

    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
    👬
    0.59
     UserDefaults
    0.51
     மாணவர்கள்
    0.51
     beneficiaries
    0.50
     informática
    0.50
    鑊
    0.50
     громадян
    0.50
    팍
    0.50
     boycot
    0.49
    फेसर
    0.49
    POSITIVE LOGITS
     платье
    1.02
     bodice
    1.00
     Bridal
    0.94
     váy
    0.92
     corset
    0.89
     bridal
    0.87
    👗
    0.87
     skirt
    0.86
     Dresses
    0.83
    bridal
    0.82
    Activations Density 0.181%

    No Known Activations