© 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. 34-GEMMASCOPE-RES-131K
    7. 93517
    Prev
    Next
    INDEX
    Explanations

    foreign language or multicultural contexts

    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
     amazing
    -1.05
     =
    -1.01
     -
    -0.99
    ari
    -0.94
     awesome
    -0.94
     extremely
    -0.93
     incredibly
    -0.93
     нормы
    -0.92
     <=
    -0.92
    za
    -0.91
    POSITIVE LOGITS
    时的
    1.06
    Nuorodos
    1.01
    时
    0.99
    且
    0.96
     Тогда
    0.93
    墬
    0.91
    小行星
    0.89
    Köszi
    0.86
    しかも
    0.86
    <0xA3>
    0.86
    Activations Density 0.076%

    No Known Activations