© 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. 9896
    Prev
    Next
    INDEX
    Explanations

    application, applications

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

    application development and deployment

    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
    胚
    0.40
    촐
    0.40
     désigne
    0.39
    フランス
    0.38
    판
    0.38
    чними
    0.38
    ตาล
    0.38
    instrList
    0.37
    粒
    0.37
    タル
    0.37
    POSITIVE LOGITS
     application
    0.64
     Application
    0.64
     APPLICATION
    0.63
    Application
    0.63
     aplicación
    0.59
     aplikasi
    0.59
     applications
    0.58
     एप्लीकेशन
    0.57
     applicationId
    0.57
    APPLICATION
    0.56
    Activations Density 0.004%

    No Known Activations