© 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-16K
    7. 12588
    Prev
    Next
    INDEX
    Explanations

    luxury, class, and elegance

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

    luxury and formality

    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_16k_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
    ت
    0.84
    L
    0.62
    ع
    0.60
    ط
    0.60
    Jo
    0.59
    కు
    0.59
    JO
    0.59
    0.58
     terapeut
    0.56
    أ
    0.55
    POSITIVE LOGITS
     luxury
    1.05
     luxurious
    1.02
     mewah
    0.99
     luxuries
    0.98
     aristocratic
    0.96
     роско
    0.96
    luxury
    0.94
     Luxurious
    0.93
    Luxury
    0.91
     Luxury
    0.90
    Activations Density 1.864%

    No Known Activations