© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93800
    Prev
    Next
    INDEX
    Explanations

    Medical University, Clinical Hospital, Landscape Park, Secret Worlds, Surgeon

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

    names of Polish places, institutions, and geographical locations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Abraço
    -0.90
    Abraços
    -0.87
     краї
    -0.84
     oryginal
    -0.82
     Ř
    -0.82
     lamella
    -0.79
    clearpage
    -0.79
    ⅽ
    -0.77
    向けの
    -0.76
     służ
    -0.76
    POSITIVE LOGITS
    宜
    0.91
    unched
    0.85
     constituency
    0.83
     Magdal
    0.83
     Cáceres
    0.82
    ,(
    0.82
    Fernseh
    0.82
    Einige
    0.82
    wußt
    0.81
    LU
    0.81
    Activations Density 0.012%

    No Known Activations