© 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. 254414
    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
     қи
    0.55
    诙
    0.52
     readability
    0.49
    повід
    0.48
     behö
    0.47
     dataGridView
    0.47
     ដ
    0.47
    。“
    0.47
     ян
    0.46
    分钟
    0.46
    POSITIVE LOGITS
    employees
    0.55
    Employees
    0.54
    Employee
    0.52
     STATE
    0.50
    SC
    0.49
     Str
    0.49
     Employee
    0.48
    OrderBy
    0.47
     SC
    0.47
    require
    0.46
    Activations Density 0.001%

    No Known Activations