© 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. 237707
    Prev
    Next
    INDEX
    Explanations

    delegate, missing

    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
    妤
    0.47
    пример
    0.45
     paragon
    0.45
    ly
    0.45
    幵
    0.44
    柟
    0.44
    და
    0.43
     ضمن
    0.43
    امج
    0.43
    du
    0.42
    POSITIVE LOGITS
     étaient
    0.55
     nowy
    0.52
    ା
    0.50
     były
    0.50
     térmica
    0.50
     vieux
    0.50
     waren
    0.49
    서울
    0.49
     hôtels
    0.49
    넓
    0.48
    Activations Density 0.001%

    No Known Activations