© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39471
    Prev
    Next
    INDEX
    Explanations

    violence and unrest

    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
    </h3>
    -1.95
    酲
    -1.55
     و
    -1.54
        
    -1.41
       
    -1.36
    years
    -1.34
    zeera
    -1.33
    ড
    -1.30
    !
    -1.29
    plevel
    -1.27
    POSITIVE LOGITS
     have
    1.30
     sportowe
    1.26
    見えます
    1.25
     الشرطة
    1.23
     вони
    1.23
    Medication
    1.23
    рпи
    1.21
     Mereka
    1.20
     ihnen
    1.20
    がありました
    1.18
    Activations Density 0.037%

    No Known Activations