© 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. 41-GEMMASCOPE-2-RES-262K
    7. 57200
    Prev
    Next
    INDEX
    Explanations

    plastic packaging wrap sealed

    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_all/layer_41_width_262k_l0_big
    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
    decorate
    0.41
     Taliban
    0.39
    ᔪ
    0.38
     royal
    0.37
    ಲಾಗ
    0.37
     furnishing
    0.37
     तालुक
    0.37
    豎
    0.37
     Kalk
    0.36
     অনুসন্ধান
    0.36
    POSITIVE LOGITS
     blister
    1.18
     blisters
    1.05
    packaged
    0.82
     packs
    0.81
     packaging
    0.80
     packaged
    0.79
    Packaging
    0.77
    packaging
    0.74
     Packs
    0.73
     Packaging
    0.72
    Activations Density 0.004%

    No Known Activations