Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 1663
    Prev
    Next
    INDEX
    Explanations

    vendors, booths, and stalls

    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
     monthly
    0.48
     principled
    0.43
     Monthly
    0.43
    Monthly
    0.42
    
    0.42
     princípios
    0.41
     hypothesized
    0.40
     unimportant
    0.40
     semesters
    0.39
    诅
    0.39
    POSITIVE LOGITS
     vendors
    1.36
     booths
    1.35
     Vendors
    1.29
     exhibitors
    1.27
    vendors
    1.21
     booth
    1.13
     stalls
    1.13
     vendor
    1.11
     Vendor
    1.06
     tents
    1.05
    Activations Density 0.012%

    No Known Activations