© 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. 31-GEMMASCOPE-2-RES-262K
    7. 14663
    Prev
    Next
    INDEX
    Explanations

    Groovy for Android and Kotlin

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

    Kotlin and Gradle build configurations

    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_31_width_262k_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
     Newfoundland
    0.48
    妫
    0.47
     funerals
    0.47
     diarrhea
    0.46
     নিঃসন্দে
    0.46
     roadways
    0.46
     fecal
    0.46
     fuelwood
    0.45
     sneezing
    0.45
    🛖
    0.45
    POSITIVE LOGITS
    Android
    0.85
    Kotlin
    0.82
     gradle
    0.82
    gradle
    0.76
    android
    0.75
    kotlin
    0.75
     Gradle
    0.74
    安卓
    0.73
    ANDROID
    0.73
     андроид
    0.73
    Activations Density 0.000%

    No Known Activations