© 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. 250527
    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
    \
    0.50
    Formation
    0.50
    Kind
    0.48
    '
    0.48
    य
    0.48
    .
    0.48
    Collect
    0.46
    раў
    0.46
    和
    0.46
    كم
    0.45
    POSITIVE LOGITS
    iacute
    0.51
    ابات
    0.50
     conspiring
    0.48
    society
    0.48
    testimonial
    0.48
     sabiduría
    0.46
    angsa
    0.46
    abin
    0.46
    reactivex
    0.45
    től
    0.45
    Activations Density 0.001%

    No Known Activations