© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4142
    Prev
    Next
    INDEX
    Explanations

    Austria and Hungary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     analizar
    2.06
    Encript
    2.00
     Valladolid
    2.00
     gegevens
    1.93
    뗄
    1.93
     appending
    1.92
    ULONG
    1.91
    紶
    1.89
     wobei
    1.88
     linguistique
    1.86
    POSITIVE LOGITS
    ers
    1.11
    home
    0.90
    from
    0.87
     Graz
    0.87
     Homemade
    0.85
     Austria
    0.83
     Exempt
    0.83
    estyle
    0.82
    hoes
    0.82
     Home
    0.81
    Activations Density 0.009%

    No Known Activations