© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215023
    Prev
    Next
    INDEX
    Explanations

    building a plane while flying it

    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
     commemoration
    0.42
    年の
    0.41
     উক্ত
    0.40
    cust
    0.40
    年は
    0.40
    鸦
    0.40
    priority
    0.40
    arranty
    0.39
    ርሃ
    0.39
    Priority
    0.39
    POSITIVE LOGITS
     Forst
    0.46
     క్ర
    0.42
    溸
    0.40
     zul
    0.39
     scout
    0.38
     उत्
    0.38
     sheets
    0.38
     mals
    0.38
     seb
    0.38
     прави
    0.37
    Activations Density 0.001%

    No Known Activations