© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11614
    Prev
    Next
    INDEX
    Explanations

    programes, un, una, és

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yki
    0.38
     Tafel
    0.38
    am
    0.38
    iz
    0.38
    軲
    0.38
     Spiegel
    0.37
    وبر
    0.37
     ......
    0.37
    jes
    0.36
    widetilde
    0.36
    POSITIVE LOGITS
    ″
    0.42
    ̵
    0.40
     περισσότε
    0.38
     horário
    0.36
     incessantly
    0.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.34
     crore
    0.34
    ⁣
    0.34
    ′
    0.34
    ⋅
    0.34
    Activations Density 0.000%

    No Known Activations