© 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. 31-GEMMASCOPE-2-RES-262K
    7. 28548
    Prev
    Next
    INDEX
    Explanations

    input scenarios

    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_31_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
    College
    0.43
    Sept
    0.43
    enumi
    0.43
     มิถุนายน
    0.42
    교육
    0.41
     питань
    0.38
    陶瓷
    0.38
     段
    0.38
    ﻌ
    0.38
    ⺀
    0.38
    POSITIVE LOGITS
     wait
    0.44
     stead
    0.42
     lenders
    0.42
     audi
    0.41
     waited
    0.40
     obec
    0.38
     instead
    0.38
     tecn
    0.38
     option
    0.37
     deduct
    0.37
    Activations Density 0.000%

    No Known Activations