© 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. 224376
    Prev
    Next
    INDEX
    Explanations

    explaining keywords or missed items

    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
     principle
    0.41
    cans
    0.36
    enco
    0.35
    <mask>
    0.34
    ™
    0.34
     Healthy
    0.33
    巾
    0.33
     ஆக
    0.32
     Production
    0.32
     щ
    0.32
    POSITIVE LOGITS
     দক্ষি
    0.41
    versammlung
    0.41
    adoff
    0.40
     freshwater
    0.40
    Southern
    0.39
     Wimbledon
    0.38
    Открыть
    0.38
     silla
    0.38
     దక్షిణ
    0.38
    UIView
    0.37
    Activations Density 0.002%

    No Known Activations