© 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-16K
    7. 10836
    Prev
    Next
    INDEX
    Explanations

    dedicated development teams

    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_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
     Russian
    0.55
     russian
    0.51
     rubles
    0.50
     z
    0.50
     zd
    0.50
     akt
    0.48
    ロシア
    0.48
     ruso
    0.48
     efekt
    0.47
     Ukrain
    0.47
    POSITIVE LOGITS
     చక్కెర
    0.57
    وزیشن
    0.54
     অ্যান
    0.53
    学术
    0.52
    ຜູ້
    0.51
    কোনও
    0.51
     வித்தியாச
    0.51
     statunitense
    0.51
    嫵
    0.50
    Соцмережа
    0.50
    Activations Density 0.033%

    No Known Activations