© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7605
    Prev
    Next
    INDEX
    Explanations

    Java programming language libraries

    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_16k_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
     cidades
    0.36
     ď
    0.33
    わたし
    0.33
    和社会
    0.33
       
    0.33
     янва
    0.33
    ↵↵↵
    0.33
    на
    0.33
     ciências
    0.32
    回应
    0.32
    POSITIVE LOGITS
    illiams
    0.41
     pectoral
    0.39
     permitem
    0.38
    ravenous
    0.37
    umlahan
    0.37
     backpacking
    0.36
     Ninety
    0.36
     ভিট
    0.36
    jacobian
    0.36
    obb
    0.36
    Activations Density 0.025%

    No Known Activations