© 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. 53-GEMMASCOPE-2-RES-262K
    7. 12784
    Prev
    Next
    INDEX
    Explanations

    Basque verb conjugations

    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_53_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
     trims
    0.44
    ếp
    0.38
     Ng
    0.37
     आजा
    0.37
     탈
    0.37
    Ng
    0.36
    രം
    0.36
     apes
    0.36
    ấ
    0.36
     藤
    0.35
    POSITIVE LOGITS
     dut
    0.60
     dute
    0.57
     zuten
    0.56
     da
    0.55
     ditu
    0.55
     duen
    0.54
     да
    0.54
     dago
    0.53
     dit
    0.52
     dau
    0.52
    Activations Density 0.006%

    No Known Activations