© 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-262K
    7. 47631
    Prev
    Next
    INDEX
    Explanations

    commit/patch diffs

    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
     ଅ
    0.41
    idefinite
    0.40
     굉장히
    0.40
     Unterstüt
    0.40
     srand
    0.40
     იყ
    0.39
    নীতিক
    0.38
    єкт
    0.37
     certificados
    0.37
     গুরুত্বপূর্ণ
    0.37
    POSITIVE LOGITS
    Robin
    0.39
    روض
    0.38
    篌
    0.38
    تنا
    0.36
     टा
    0.35
    rossovers
    0.35
    Harvey
    0.34
    Iso
    0.34
    قت
    0.34
    これ
    0.34
    Activations Density 0.000%

    No Known Activations