© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35077
    Prev
    Next
    INDEX
    Explanations

    extension of earlier work

    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
    dienne
    -1.08
    
    -1.04
     quatre
    -1.02
     borboleta
    -0.98
     deux
    -0.97
    ebly
    -0.97
     aproximado
    -0.94
     gorra
    -0.94
     asla
    -0.94
     tüm
    -0.93
    POSITIVE LOGITS
     already
    2.28
     existing
    1.91
    already
    1.62
     già
    1.59
     уже
    1.55
    existing
    1.41
    Already
    1.40
     Already
    1.33
     bereits
    1.25
    すでに
    1.18
    Activations Density 0.093%

    No Known Activations