© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10308
    Prev
    Next
    INDEX
    Explanations

    client access, authentication, and components

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

    client-side operations

    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
    一道
    0.43
     Сим
    0.43
    ｽ
    0.42
    י
    0.42
    شوند
    0.42
    سری
    0.41
     Старки
    0.41
    ี้ยง
    0.41
    يون
    0.40
     води
    0.40
    POSITIVE LOGITS
    ToServer
    0.81
     client
    0.71
     side
    0.66
     Client
    0.65
    サイド
    0.62
     klient
    0.60
    getClient
    0.60
    측
    0.59
     CLIENT
    0.58
    SIDE
    0.58
    Activations Density 0.056%

    No Known Activations