© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72515
    Prev
    Next
    INDEX
    Explanations

    programming operators and keywords

    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
    鸰
    -2.39
    他现在
    -2.16
     菓子
    -2.11
    グルト
    -2.08
    他没有
    -2.08
    先日
    -2.06
    Пі
    -2.05
    今月
    -2.02
    Ketika
    -2.00
    ーズン
    -1.98
    POSITIVE LOGITS
     also
    2.52
     Does
    1.96
    служба
    1.95
     Where
    1.93
     Should
    1.92
    不宜
    1.88
     افرادی
    1.88
     like
    1.86
     we
    1.84
     Comparing
    1.76
    Activations Density 0.001%

    No Known Activations