© 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. 78385
    Prev
    Next
    INDEX
    Explanations

    object types in programming code

    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
    had
    -0.95
     Sad
    -0.75
    信息的
    -0.74
    angel
    -0.73
    FloatField
    -0.73
     Aussch
    -0.72
    mani
    -0.70
     tú
    -0.69
    ussch
    -0.69
    ุต
    -0.68
    POSITIVE LOGITS
     object
    1.47
    object
    1.27
     Object
    1.20
    Object
    1.14
    UObject
    1.04
     objects
    0.99
    QObject
    0.91
     UnityEngine
    0.88
     NSObject
    0.88
     OBJECT
    0.85
    Activations Density 0.020%

    No Known Activations