© 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. 40-GEMMASCOPE-2-RES-262K
    7. 168968
    Prev
    Next
    INDEX
    Explanations

    legally excusable, deeply offended

    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_40_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
     broker
    0.38
     Quân
    0.38
     Anglo
    0.38
    目
    0.37
     beden
    0.36
    alena
    0.36
    []
    0.36
     দিতেন
    0.35
     streamwise
    0.35
    🤣
    0.35
    POSITIVE LOGITS
    èvement
    0.46
    解消
    0.45
    commit
    0.42
     यानि
    0.41
     Disp
    0.40
     साकार
    0.39
     متعلق
    0.39
     विकार
    0.39
     zaak
    0.38
     permitem
    0.38
    Activations Density 0.000%

    No Known Activations