© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2230
    Prev
    Next
    INDEX
    Explanations

    painted symbols and decorations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     landfills
    0.88
     fisik
    0.75
     Fiz
    0.72
    躬
    0.70
    浊
    0.68
     fisica
    0.68
     nevo
    0.68
    啞
    0.68
     Kobayashi
    0.67
     abandoned
    0.67
    POSITIVE LOGITS
     carvings
    1.70
     decoration
    1.64
     decorations
    1.51
     ornamentation
    1.49
     carving
    1.42
     Decoration
    1.41
     decorate
    1.41
     carved
    1.40
     decorating
    1.33
    Decor
    1.32
    Activations Density 0.350%

    No Known Activations