© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77554
    Prev
    Next
    INDEX
    Explanations

    figure 1 citation

    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
     kerjasama
    -0.99
     chré
    -0.96
     should
    -0.94
     bantuan
    -0.93
    ΕΣ
    -0.87
    ΑΡ
    -0.87
     bekämp
    -0.87
     üzerinden
    -0.84
     situasi
    -0.84
     viena
    -0.83
    POSITIVE LOGITS
     A
    1.18
     B
    1.01
    iiii
    0.96
    A
    0.85
     verder
    0.84
    lucky
    0.83
    ᾽
    0.82
     ní
    0.82
     C
    0.81
    B
    0.81
    Activations Density 0.013%

    No Known Activations