© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130634
    Prev
    Next
    INDEX
    Explanations

    building

    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
    ية
    -2.09
     姆
    -2.05
    traueranzeige
    -2.05
    的白
    -2.03
    푘
    -2.02
    的在
    -1.99
     vraiment
    -1.98
    Возраст
    -1.95
    Ответить
    -1.93
    isbury
    -1.92
    POSITIVE LOGITS
    <bos>
    3.11
    )?
    2.42
     providing
    2.27
     If
    2.13
    与此同时
    2.09
    .”)
    2.08
    ઁ
    2.06
    亊
    2.05
     using
    2.03
    结语
    2.03
    Activations Density 0.011%

    No Known Activations