© 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. 3570
    Prev
    Next
    INDEX
    Explanations

    different nations, industries, applications

    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
    isa
    0.30
    öffnet
    0.27
     kemudian
    0.27
    uckland
    0.27
     然后
    0.27
     でも
    0.27
     అనేది
    0.27
    𝒔
    0.27
    𝑏
    0.27
     ដោយ
    0.27
    POSITIVE LOGITS
    異なる
    0.31
    pecific
    0.29
     frequented
    0.29
     перечис
    0.28
     разные
    0.28
     distintas
    0.27
     juntas
    0.27
    特定の
    0.26
     listed
    0.26
     poput
    0.26
    Activations Density 0.822%

    No Known Activations