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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14689
    Prev
    Next
    INDEX
    Explanations

    course designations and grades

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

    numbers and codes

    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_16k_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
    構築
    0.44
     éléments
    0.44
     handling
    0.42
     progressBar
    0.42
     primitives
    0.42
     snippets
    0.41
    ₁,
    0.41
    สำหรับการ
    0.41
    ₁
    0.41
     চাইছে
    0.40
    POSITIVE LOGITS
    Bryan
    0.43
    हुआ
    0.42
    Western
    0.41
    Traditional
    0.40
     Bryan
    0.40
    ারা
    0.39
    साल
    0.39
     Тол
    0.39
    Ю
    0.39
    멧
    0.39
    Activations Density 0.023%

    No Known Activations