© 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. 14133
    Prev
    Next
    INDEX
    Explanations

    concepts of worlds

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

    world of X

    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
     يدل
    0.47
     سنوات
    0.47
    雹
    0.46
    衅
    0.46
     عمليات
    0.45
    كيل
    0.45
    等人
    0.45
    সহ
    0.45
    濟
    0.44
     года
    0.44
    POSITIVE LOGITS
     realm
    0.57
     jossa
    0.55
     mundo
    0.54
     where
    0.52
     vast
    0.51
     worlds
    0.49
     świata
    0.47
    Worlds
    0.47
     abyss
    0.46
     Worlds
    0.46
    Activations Density 0.065%

    No Known Activations