© 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. 60189
    Prev
    Next
    INDEX
    Explanations

    Q followed by Kerr, Questions and Women

    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
    エンジ
    -0.98
     овощи
    -0.82
     šte
    -0.82
     Otros
    -0.81
     utterly
    -0.80
     greatly
    -0.80
    ประก
    -0.80
     most
    -0.80
     contaba
    -0.79
    Specifik
    -0.79
    POSITIVE LOGITS
    asilkan
    0.98
     Torrance
    0.94
     thesis
    0.93
     theses
    0.93
     ní
    0.93
    anceled
    0.92
    atc
    0.91
    繚
    0.91
     CONTIN
    0.91
     grima
    0.91
    Activations Density 0.000%

    No Known Activations