© 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. 54470
    Prev
    Next
    INDEX
    Explanations

    functions describing or listing

    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
    ας
    0.59
     Тому
    0.57
     того
    0.54
     Obrigado
    0.54
     .+
    0.51
     कार्यक्रमों
    0.51
     Fukuoka
    0.50
     pajak
    0.50
     बाई
    0.50
    ၵ
    0.50
    POSITIVE LOGITS
     are
    0.89
     is
    0.80
    represents
    0.77
     consists
    0.75
     contains
    0.74
     είναι
    0.71
    は
    0.69
    是
    0.68
     represents
    0.66
     является
    0.66
    Activations Density 0.023%

    No Known Activations