© 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. 104138
    Prev
    Next
    INDEX
    Explanations

    larger [noun]

    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
     
    -3.42
     This
    -2.56
    </b>
    -2.55
     ciertamente
    -2.42
     Pokud
    -2.42
    に入る
    -2.23
     Při
    -2.19
    
    -2.14
     بالإضافة
    -2.14
    ющие
    -2.13
    POSITIVE LOGITS
    ሖ
    2.80
    〜。
    2.78
    st
    2.73
    ᠂
    2.73
    。】
    2.70
    ه‌ی
    2.58
    al
    2.52
    های
    2.47
     facendo
    2.47
     ataupun
    2.44
    Activations Density 0.005%

    No Known Activations