© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 193977
    Prev
    Next
    INDEX
    Explanations

    futuristic design and luxury

    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
     महाराष्ट
    0.45
     assaulted
    0.43
    ῇ
    0.43
     ''),
    0.43
     assaults
    0.43
    ИС
    0.43
    ⚋
    0.42
     outraged
    0.41
    CONST
    0.41
    Интернет
    0.41
    POSITIVE LOGITS
     VIA
    0.47
     lux
    0.47
    🥳
    0.47
     Design
    0.47
     Luxury
    0.47
     Specifications
    0.46
     வடிவமை
    0.45
     Kitchen
    0.44
     ছাড়াও
    0.44
    Design
    0.43
    Activations Density 0.006%

    No Known Activations