© 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. 44389
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    Here's a guide

    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
    ↵↵
    0.39
    ↵
    0.33
    because
    0.33
     Especially
    0.32
    this
    0.32
     because
    0.31
    也就是说
    0.31
    ↵↵↵
    0.30
     Because
    0.30
    ↵↵↵↵
    0.30
    POSITIVE LOGITS
    
    0.28
    ᶤ
    0.28
     lembut
    0.27
    മ്ബ
    0.27
     ankaŭ
    0.27
     coû
    0.27
    ၿ
    0.26
     diğer
    0.26
     perfekte
    0.26
     bruge
    0.25
    Activations Density 0.019%

    No Known Activations