© 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. 34902
    Prev
    Next
    INDEX
    Explanations

    charter, Magna Carta, charters

    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
     สี
    0.44
    deserialize
    0.40
    สี
    0.39
     بیک
    0.39
     serpentine
    0.38
     ক্ষেপণাস্ত্র
    0.38
    Gosudarstvennyj
    0.38
     색
    0.37
     inoxyd
    0.37
     الزد
    0.37
    POSITIVE LOGITS
     charter
    2.47
     Charter
    2.34
    Charter
    2.23
     charters
    2.08
     chartered
    1.60
     Chartered
    1.44
     चार्ट
    1.35
    char
    1.25
     char
    1.24
     Char
    1.09
    Activations Density 0.001%

    No Known Activations