© 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. 10-GEMMASCOPE-RES-131K
    7. 104655
    Prev
    Next
    INDEX
    Explanations

    footnote references

    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
    تیجه
    -2.09
    Ārējās
    -2.06
     Actually
    -2.02
    Ꮼ
    -1.97
    ญี่ป
    -1.96
     There
    -1.95
     Selain
    -1.92
    citroen
    -1.91
     Contoh
    -1.84
     Oft
    -1.78
    POSITIVE LOGITS
    </strong>
    2.31
    
    2.23
    ↵
    2.19
     продолжает
    2.14
    ו
    2.13
    们的
    2.11
     để
    2.09
    <em>
    2.05
     スペシャル
    2.03
    圌
    2.02
    Activations Density 0.003%

    No Known Activations