© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167397
    Prev
    Next
    INDEX
    Explanations

    to put it

    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
    인데요
    0.42
    ovi
    0.40
    인데
    0.38
    깃
    0.37
     wherein
    0.36
    веду
    0.36
    ники
    0.36
    領
    0.34
    iau
    0.34
    न्तु
    0.34
    POSITIVE LOGITS
     zumindest
    0.46
     อ่า
    0.45
     cliché
    0.45
     unbek
    0.42
     aproximadamente
    0.41
     decirlo
    0.41
    啧
    0.41
     حسب
    0.41
    Overall
    0.39
     palabras
    0.39
    Activations Density 0.012%

    No Known Activations