© 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. 206733
    Prev
    Next
    INDEX
    Explanations

    following normal actions

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

    specific terms

    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
    oja
    0.51
    ᱪ
    0.50
    をご覧ください
    0.50
    კი
    0.49
    ニューヨーク
    0.49
    пиа
    0.48
    ｙ
    0.48
    ぜひ
    0.48
    ื่ม
    0.47
    Nya
    0.47
    POSITIVE LOGITS
     number
    0.54
     عدد
    0.54
     monogram
    0.53
     Albrecht
    0.50
     Kolmogorov
    0.49
     calibr
    0.49
     Obwohl
    0.49
     ******
    0.47
     số
    0.47
     ornith
    0.46
    Activations Density 0.001%

    No Known Activations