© 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. 22-GEMMASCOPE-RES-131K
    7. 72238
    Prev
    Next
    INDEX
    Explanations

    query and search code structures

    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
    鲤
    -0.94
    assure
    -0.86
     activation
    -0.82
     architekt
    -0.82
    llä
    -0.82
    nóstico
    -0.81
     Đây
    -0.81
     için
    -0.81
    Civic
    -0.80
    捩
    -0.79
    POSITIVE LOGITS
     query
    1.07
     searching
    1.05
     search
    1.02
    請問
    1.00
    亲爱的
    0.94
     searches
    0.94
    ASKET
    0.90
    您可以
    0.89
    ३
    0.88
    ｇ
    0.88
    Activations Density 0.002%

    No Known Activations