© 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. 74334
    Prev
    Next
    INDEX
    Explanations

    Bermuda, Cayman, CATCo

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

    place names and numbers

    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
     नाग
    0.46
    順番
    0.40
     getContent
    0.40
    準備
    0.40
    稈
    0.40
    CUSTOMER
    0.39
    嵓
    0.39
     FAILURE
    0.38
     azy
    0.38
     MinMaxScaler
    0.38
    POSITIVE LOGITS
     Bermuda
    0.79
     Cayman
    0.69
     বাড়ির
    0.46
     Hok
    0.45
    썸
    0.44
    යු
    0.42
     Barbados
    0.41
     Yucatán
    0.40
     Berm
    0.40
     shorts
    0.39
    Activations Density 0.038%

    No Known Activations