© 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. 260884
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     computer
    0.57
     komputer
    0.57
     download
    0.54
    ↵↵↵
    0.54
     computers
    0.53
     linux
    0.53
     कंप्यूटर
    0.52
     मैं
    0.51
     tecnologías
    0.51
    process
    0.51
    POSITIVE LOGITS
    ကာ
    0.47
     მისი
    0.47
    寥
    0.45
    ירת
    0.44
     Dickinson
    0.44
     Selon
    0.42
    唳
    0.42
     "[
    0.41
     그의
    0.41
    橼
    0.41
    Activations Density 0.001%

    No Known Activations