© 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. 102226
    Prev
    Next
    INDEX
    Explanations

    framed art prints

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

    polygamy thinking apnea perfectionism

    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
     அலெ
    0.50
     வரலாற்று
    0.47
     Во
    0.46
    immä
    0.46
    淯
    0.46
     Васи
    0.45
    热爱
    0.45
     német
    0.45
    வழி
    0.45
    滹
    0.45
    POSITIVE LOGITS
     quotas
    0.55
     decoration
    0.54
    👜
    0.49
     either
    0.49
     pushing
    0.48
     pushed
    0.48
     bosses
    0.48
    decoration
    0.47
     decorations
    0.47
     push
    0.47
    Activations Density 0.000%

    No Known Activations