© 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. 3904
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
    രുന്നത്
    0.41
    وة
    0.39
     दामों
    0.39
     ware
    0.39
    िलेश
    0.38
    櫚
    0.38
     nanoparticle
    0.38
     sera
    0.37
     pedi
    0.37
     vendre
    0.37
    POSITIVE LOGITS
    0.61
             
    0.47
    imp
    0.47
    pre
    0.44
    described
    0.44
    text
    0.44
    0.44
         
    0.43
    nd
    0.43
        
    0.42
    Activations Density 0.110%

    No Known Activations