© 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. 30825
    Prev
    Next
    INDEX
    Explanations

    Aragon, Zaragoza, Leon, Excel

    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
    TComponent
    0.43
     sandy
    0.39
    ুদ
    0.38
     ukl
    0.37
    ɽ
    0.37
    ளவு
    0.37
    വധി
    0.37
    鯱
    0.37
     औपचारिक
    0.36
    withtag
    0.36
    POSITIVE LOGITS
     Aragon
    0.71
     Arag
    0.68
     Zaragoza
    0.65
     Aragón
    0.64
    arag
    0.51
     అరుణ
    0.48
     Сара
    0.46
    Arithmetic
    0.45
     Arithmetic
    0.44
     Alcan
    0.41
    Activations Density 0.002%

    No Known Activations