© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8701
    Prev
    Next
    INDEX
    Explanations

    object or instance creation

    np_acts-logits-general · gemini-2.5-flash-lite

    Create an instance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ढ़े
    0.40
    IRD
    0.39
    وری
    0.39
    漕
    0.38
    वास
    0.37
    츤
    0.37
    वाल
    0.37
    và
    0.37
    潜
    0.37
    irdik
    0.36
    POSITIVE LOGITS
     object
    1.63
    对象
    1.63
     objects
    1.56
    オブジェクト
    1.56
     objeto
    1.55
     объекта
    1.54
     объект
    1.53
     objek
    1.49
     instance
    1.48
     obiect
    1.45
    Activations Density 0.067%

    No Known Activations