© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61406
    Prev
    Next
    INDEX
    Explanations

    password policy and domain security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.39
    什么
    -1.14
    getAll
    -1.08
     vs
    -1.07
    比起
    -1.05
    太多
    -1.05
    缎
    -1.04
    межу
    -1.04
     versus
    -1.02
    strtolower
    -1.02
    POSITIVE LOGITS
    闡
    1.28
     tma
    1.26
    後面
    1.21
     toul
    1.20
     dafs
    1.18
    的一個
    1.18
    empatan
    1.16
    摻
    1.15
    ϝ
    1.13
     obicei
    1.13
    Activations Density 0.146%

    No Known Activations