© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221745
    Prev
    Next
    INDEX
    Explanations

    calendar, measure, apps, guarantee, forming, tree, Revolution

    np_acts-logits-general · gemini-2.5-flash-lite

    Tkinter or asm module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    珂
    0.48
    HOBBIT
    0.47
    EJ
    0.47
    頓
    0.46
    仲間
    0.46
     англий
    0.45
     shrewd
    0.45
     Soto
    0.45
    NJ
    0.44
     Needless
    0.44
    POSITIVE LOGITS
     unfolded
    0.52
    حدیث
    0.48
     ArrayAdapter
    0.46
    κ
    0.46
     undergoing
    0.44
    ]।
    0.42
    ادی
    0.42
    া
    0.41
     barrels
    0.41
    قیق
    0.41
    Activations Density 0.001%

    No Known Activations