© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200300
    Prev
    Next
    INDEX
    Explanations

    radiant, following, miraculous, blog, Brussels

    np_acts-logits-general · gemini-2.5-flash-lite

    ethical, moral, travel, forcing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     su
    0.51
     imprimir
    0.50
    م
    0.48
     quando
    0.48
     goof
    0.48
     claro
    0.47
     cuando
    0.47
    י
    0.46
     torneo
    0.46
     actualizado
    0.46
    POSITIVE LOGITS
    젤
    0.51
    疥
    0.50
    북
    0.49
    쐐
    0.48
    Sodium
    0.48
    KCl
    0.48
     مداخل
    0.47
    Sunflower
    0.47
    늑
    0.46
     हमलों
    0.46
    Activations Density 0.000%

    No Known Activations