© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11108
    Prev
    Next
    INDEX
    Explanations

    US, Canadian, German, American

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

    google.com country names US India

    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_40_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
    webkit
    0.39
    aholic
    0.39
    áb
    0.38
    furan
    0.38
    _|
    0.38
    Pues
    0.37
     shocking
    0.37
    রিদ্র
    0.37
     freshest
    0.37
     drama
    0.37
    POSITIVE LOGITS
    🇩
    0.55
    美国的
    0.49
    美國
    0.48
     Tux
    0.48
     US
    0.46
     இந்தியாவில்
    0.44
    加拿大
    0.43
    🇨
    0.43
    Canadian
    0.42
     यूएस
    0.42
    Activations Density 0.062%

    No Known Activations