© 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. 31-GEMMASCOPE-2-RES-262K
    7. 54718
    Prev
    Next
    INDEX
    Explanations

    current records and leaders

    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_31_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
     سپورټ
    0.57
     خیر
    0.53
     بین
    0.49
    囘
    0.48
     پیغمبر
    0.48
     теркәлү
    0.47
     дети
    0.47
    ၿ
    0.47
     भय
    0.47
    ភេទ
    0.46
    POSITIVE LOGITS
    k
    0.52
     on
    0.51
    ين
    0.49
    ,
    0.47
     ontvangen
    0.46
     hva
    0.46
    l
    0.46
    s
    0.44
     singolo
    0.43
    straat
    0.43
    Activations Density 0.002%

    No Known Activations