© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1528
    Prev
    Next
    INDEX
    Explanations

    java, terraform, promise, orm, common, arquillian, resource

    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
     its
    -0.98
    しましたが
    -0.91
     jį
    -0.90
    
    -0.85
     naudoti
    -0.84
    rror
    -0.84
    aiso
    -0.83
     τὴν
    -0.82
     declarado
    -0.82
    unteer
    -0.82
    POSITIVE LOGITS
     estes
    1.03
     corren
    0.90
    Still
    0.89
     зай
    0.85
    ɑ
    0.84
    ៈ
    0.84
     vado
    0.84
    游戏介绍
    0.83
    InsertCommand
    0.82
    ography
    0.82
    Activations Density 0.044%

    No Known Activations