© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 99739
    Prev
    Next
    INDEX
    Explanations

    void function declarations

    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_34/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
     for
    -0.93
    未来的
    -0.88
     as
    -0.88
    Various
    -0.87
    enfants
    -0.85
    七夕
    -0.84
    ltä
    -0.82
     различи
    -0.82
     Católica
    -0.80
    ཚ
    -0.80
    POSITIVE LOGITS
    )
    2.02
    )
    
    1.52
    ){
    
    1.31
    ){
    1.28
    )$
    1.10
    {*
    1.10
    RIAGE
    1.09
    *
    1.09
     billede
    1.05
    );
    
    1.02
    Activations Density 0.004%

    No Known Activations