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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31878
    Prev
    Next
    INDEX
    Explanations

    bags and their types

    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
     átomos
    0.49
     genomic
    0.49
     glycos
    0.47
     atom
    0.46
     intron
    0.45
     Pediatr
    0.44
    🧪
    0.44
     sabor
    0.44
     circumstellar
    0.44
     phyto
    0.44
    POSITIVE LOGITS
     backpacks
    1.55
     bags
    1.47
    👜
    1.45
     bag
    1.41
     Bags
    1.39
     сумка
    1.38
     backpack
    1.38
     Backpack
    1.34
     handbag
    1.32
     ব্যাগ
    1.32
    Activations Density 0.010%

    No Known Activations