© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99761
    Prev
    Next
    INDEX
    Explanations

    million pounds or dollars

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Ỳ
    -0.76
    sizable
    -0.75
    zei
    -0.73
    ταν
    -0.72
    έρ
    -0.71
    django
    -0.69
     Dealers
    -0.69
     مشارکت‌کنندگان
    -0.68
    average
    -0.68
    JACK
    -0.68
    POSITIVE LOGITS
    暄
    0.72
    icius
    0.70
     pintura
    0.69
     pickle
    0.65
    erobe
    0.65
     krie
    0.64
    Paint
    0.63
     サー
    0.63
     nucleic
    0.63
     Rahmen
    0.61
    Activations Density 0.067%

    No Known Activations