© 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. 23558
    Prev
    Next
    INDEX
    Explanations

    Bieler, Rietveld, Griesenbeck, Miesfeld

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

    surnames of German or European origin.

    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
    andidaten
    -0.87
    bj
    -0.78
    ########
    -0.75
    人工智能
    -0.74
     blij
    -0.71
    fileList
    -0.71
    inar
    -0.68
    والي
    -0.68
    glfw
    -0.68
     organising
    -0.68
    POSITIVE LOGITS
     undoing
    0.77
     whether
    0.74
    claves
    0.74
    漠
    0.72
    lient
    0.72
    AGEMENT
    0.72
     liking
    0.70
    parque
    0.69
    relate
    0.69
    asure
    0.69
    Activations Density 0.048%

    No Known Activations