© 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. 76500
    Prev
    Next
    INDEX
    Explanations

    alluring, sensing, needing, good

    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
    с
    0.43
     piani
    0.40
    alten
    0.39
    initializeApp
    0.39
    um
    0.39
     כאשר
    0.38
    external
    0.38
     штра
    0.38
     erd
    0.37
     बाहरी
    0.37
    POSITIVE LOGITS
    ADA
    0.57
    _{(\
    0.50
    ʕ
    0.49
     انسٹ
    0.48
    Ag
    0.47
     Acá
    0.47
     उनमें
    0.47
    Geplaatst
    0.46
    AKE
    0.46
    CONCLUSIONS
    0.46
    Activations Density 0.001%

    No Known Activations