© 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. 4505
    Prev
    Next
    INDEX
    Explanations

    solder, weld, connector, automotive, repair

    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
     মানবাধিকার
    0.37
     細胞
    0.37
     intellectuals
    0.36
    ッピー
    0.35
     suffrage
    0.34
     館
    0.34
    ardonnay
    0.33
     ټینس
    0.33
     فوټبال
    0.33
    🥗
    0.33
    POSITIVE LOGITS
     corrosion
    0.67
     gasket
    0.66
     solder
    0.66
     welds
    0.62
     weld
    0.61
     soldering
    0.61
     welding
    0.59
     epoxy
    0.59
     connector
    0.59
     sealant
    0.57
    Activations Density 0.124%

    No Known Activations