© 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. 23590
    Prev
    Next
    INDEX
    Explanations

    methods, policy, technology, period, terms

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

    rules and timing

    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
    ד
    0.55
    で行
    0.53
    د
    0.50
    رب
    0.49
    عمل
    0.48
     coorden
    0.44
    ردم
    0.43
    で
    0.43
    درس
    0.43
    شار
    0.42
    POSITIVE LOGITS
     অন্যদের
    0.45
     insgesamt
    0.44
     মেয়াদ
    0.44
     নগদ
    0.43
     disclosed
    0.43
    がございます
    0.42
     확보
    0.42
     अद्वितीय
    0.42
     establecido
    0.41
     স্পষ্ট
    0.41
    Activations Density 0.041%

    No Known Activations