© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 13763
    Prev
    Next
    INDEX
    Explanations

    high-end hardware and luxury vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cute
    0.47
    Celeron
    0.46
     Compact
    0.44
    峮
    0.42
     Cute
    0.42
     Corbyn
    0.42
    Small
    0.41
    Compact
    0.41
     Condensed
    0.41
     cute
    0.41
    POSITIVE LOGITS
     luxury
    0.77
     роско
    0.71
     Luxury
    0.70
    Luxury
    0.69
     behem
    0.69
     flagship
    0.67
    luxury
    0.67
     luxurious
    0.67
    奢
    0.65
     stately
    0.63
    Activations Density 0.032%

    No Known Activations