© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65959
    Prev
    Next
    INDEX
    Explanations

    EndInit, InitializeComponent

    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
     which
    -1.13
     their
    -1.00
     kepad
    -0.87
     by
    -0.87
    </h3>
    -0.82
    isseurs
    -0.81
     there
    -0.81
     usually
    -0.79
     then
    -0.79
     about
    -0.79
    POSITIVE LOGITS
    EndInit
    1.13
    BeginInit
    1.13
    屿
    1.01
    够了
    0.90
    も行
    0.89
    ᾠ
    0.89
    极其
    0.88
     resourceCulture
    0.88
    Antwoord
    0.86
    绑定
    0.86
    Activations Density 0.001%

    No Known Activations