© 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. 29690
    Prev
    Next
    INDEX
    Explanations

    Mapping Early Modern World

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

    explaining topics and how-to guides

    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
     कहे
    0.41
    ྗ
    0.40
    っいて
    0.40
    ް
    0.39
    ḕ
    0.38
    슘
    0.38
    ޖ
    0.37
    ﺘ
    0.37
    高兴
    0.37
     initialise
    0.37
    POSITIVE LOGITS
     كيفية
    0.45
    www
    0.44
    
    0.40
    Linking
    0.39
    Authorized
    0.39
    https
    0.38
    Analytics
    0.38
     tých
    0.38
    Dimensions
    0.38
     SRL
    0.37
    Activations Density 0.001%

    No Known Activations