© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46055
    Prev
    Next
    INDEX
    Explanations

    formal agreement, report, announcement, letter

    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_65k_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
    ponin
    0.39
    碼
    0.39
    Coordinator
    0.38
    ঙ্কা
    0.38
    śmy
    0.38
     неделю
    0.38
     वैरिएंट
    0.38
     intravenously
    0.38
     তিনজন
    0.37
    Ц
    0.37
    POSITIVE LOGITS
     প্রভৃতি
    0.61
     ইত্যাদি
    0.59
     മറ്റു
    0.55
     Etc
    0.55
     autres
    0.54
     herhangi
    0.52
     financiación
    0.52
     etc
    0.51
     கல்வி
    0.51
     Islamic
    0.50
    Activations Density 0.010%

    No Known Activations