© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 49918
    Prev
    Next
    INDEX
    Explanations

    yo mama and science experiments

    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_65k_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
     strtoupper
    0.41
     [...
    0.41
    Documentation
    0.40
     Documentation
    0.40
    valid
    0.40
     gelen
    0.39
     Ide
    0.39
    原始
    0.38
    Sto
    0.38
    Combin
    0.38
    POSITIVE LOGITS
     பெற
    0.41
    ᓱ
    0.37
     హైదర్
    0.37
     ಕೂಡ
    0.36
     beetles
    0.35
    nél
    0.35
     منسلک
    0.35
     customs
    0.35
     ruler
    0.35
    办公
    0.35
    Activations Density 0.002%

    No Known Activations