© 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. 22-GEMMASCOPE-RES-131K
    4. 66796
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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_22/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
     it
    -1.97
     like
    -1.27
    回来了
    -1.20
     its
    -1.20
     and
    -1.15
     so
    -1.15
     companies
    -1.14
     at
    -1.10
     има
    -1.10
     one
    -1.09
    POSITIVE LOGITS
    Hilsen
    1.33
    がありますが
    1.32
    虽说
    1.27
    Debido
    1.25
     Поэтому
    1.23
    ᡴ
    1.20
     Однако
    1.18
    Análisis
    1.16
    兩
    1.13
    不应该
    1.13
    Activations Density 0.001%

    No Known Activations