© 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. 79033
    Prev
    Next
    INDEX
    Explanations

    locations, services, and prices

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

    make money, last, person, methods, layout, sign up, cost, wholesale, sale, strategies

    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
    Isometric
    0.46
    е
    0.45
    ное
    0.44
    рия
    0.43
    الأ
    0.43
    ц
    0.43
    ért
    0.42
     सुपरस्टार
    0.42
     copyspace
    0.41
    ➨
    0.40
    POSITIVE LOGITS
     رکھتے
    0.39
     TUM
    0.34
     admon
    0.34
     یافته
    0.34
     (?)
    0.34
     Tm
    0.34
     Packet
    0.34
     Scriptures
    0.34
     concerns
    0.33
     packet
    0.33
    Activations Density 0.082%

    No Known Activations