© 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. 158571
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    foreign languages or specific entities

    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
    cited
    0.53
    now
    0.48
    ಲಿಲ್ಲ
    0.46
    і
    0.46
    url
    0.45
    ю
    0.45
     cited
    0.43
    cost
    0.42
     justified
    0.42
    agency
    0.42
    POSITIVE LOGITS
     sogenannte
    0.49
     अभि
    0.46
     Départ
    0.45
     schließlich
    0.45
     ולא
    0.45
    杏
    0.45
    چار
    0.44
     privile
    0.44
    AppConstant
    0.44
     ehemalige
    0.44
    Activations Density 0.001%

    No Known Activations