© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 228100
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    zinho
    0.62
    á
    0.58
    dison
    0.57
    zás
    0.55
    úč
    0.54
    í
    0.54
    áce
    0.52
    чками
    0.52
    ábamos
    0.52
    键
    0.52
    POSITIVE LOGITS
     drugs
    0.46
     ceramics
    0.41
     cytology
    0.41
     waffles
    0.40
     cigarettes
    0.40
     rất
    0.39
     তখনও
    0.39
     fireworks
    0.39
     groceries
    0.39
     calligraphy
    0.39
    Activations Density 0.000%

    No Known Activations