© 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. 168922
    Prev
    Next
    INDEX
    Explanations

    prioritization, observing, or skipping

    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
     czy
    0.39
     ン
    0.39
     Các
    0.38
     risque
    0.38
     허
    0.38
    റ്റ്‌
    0.38
     Giá
    0.37
     fare
    0.37
     цін
    0.37
     risked
    0.36
    POSITIVE LOGITS
     سرعت
    0.43
     subalgebra
    0.41
     eigenstates
    0.41
    逮
    0.40
     Sensing
    0.39
    uega
    0.38
     दाएं
    0.38
    //}
    0.37
     Veamos
    0.37
     svega
    0.37
    Activations Density 0.003%

    No Known Activations