© 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. 128571
    Prev
    Next
    INDEX
    Explanations

    file existence checks

    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
    cels
    -1.06
    ofy
    -1.05
    alucía
    -1.03
    ignment
    -1.01
                                  
    -1.01
    rightarrow
    -1.01
    cinoma
    -0.99
                
    -0.98
     учащихся
    -0.97
    ación
    -0.96
    POSITIVE LOGITS
     説明
    0.97
    きている
    0.96
     信息
    0.93
    ayaquil
    0.91
    existe
    0.91
     condizione
    0.91
     個人
    0.90
     名称
    0.88
    Dispon
    0.88
    autoload
    0.88
    Activations Density 0.013%

    No Known Activations