© 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. 177617
    Prev
    Next
    INDEX
    Explanations

    either or either, suddenly, Shirakawa, mind's eye

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

    specific attributes or states

    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
     agli
    0.54
    خبر
    0.54
    រ
    0.53
     strane
    0.52
    ږ
    0.51
    ര
    0.50
    劍
    0.50
    بە
    0.50
    figs
    0.50
     Naras
    0.49
    POSITIVE LOGITS
     testifies
    0.44
     使っ
    0.40
    ayv
    0.40
     使用
    0.39
    âtres
    0.39
     использования
    0.39
     causative
    0.39
     ketogenic
    0.39
     designee
    0.39
    道府県
    0.38
    Activations Density 0.000%

    No Known Activations