© 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-262K
    7. 110241
    Prev
    Next
    INDEX
    Explanations

    orders, procedures, and descriptions of advanced skills

    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
     Ex
    0.50
     hyped
    0.48
     Crowns
    0.45
     Edison
    0.44
     Crown
    0.44
     glasses
    0.43
     celsius
    0.43
    ր
    0.43
     enthusi
    0.43
     (),
    0.43
    POSITIVE LOGITS
    Toolkit
    0.51
     нож
    0.50
     нача
    0.50
    Describe
    0.50
    Procedure
    0.50
     ദു
    0.50
    く
    0.48
    鏉
    0.48
    lable
    0.48
    Code
    0.47
    Activations Density 0.006%

    No Known Activations