© 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. 72541
    Prev
    Next
    INDEX
    Explanations

    those or that

    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
    病例
    -0.96
    //});
    -0.91
     soprattutto
    -0.91
     nossos
    -0.87
    chambre
    -0.84
    ankind
    -0.83
     presentó
    -0.81
    看书
    -0.81
    時には
    -0.80
    ıyoruz
    -0.80
    POSITIVE LOGITS
     tersebut
    1.46
    はその
    1.34
     those
    1.33
    その
    1.22
    นั้น
    1.13
     उस
    1.05
    лови
    1.05
     that
    1.05
    Those
    1.04
    那个
    1.02
    Activations Density 0.088%

    No Known Activations