© 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. 86941
    Prev
    Next
    INDEX
    Explanations

    bre, stra, atre, bra

    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
    圌
    -2.89
    
    -2.80
     všech
    -2.61
     hade
    -2.59
    就去
    -2.58
     ſou
    -2.48
     masterful
    -2.48
    うーん
    -2.47
    Ɑ
    -2.47
    是想
    -2.44
    POSITIVE LOGITS
     There
    3.16
    蛧
    2.83
     While
    2.73
    ly
    2.66
     This
    2.58
     Despite
    2.52
    </>
    2.52
     When
    2.45
    逦
    2.45
     Many
    2.41
    Activations Density 0.120%

    No Known Activations