© 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. 58839
    Prev
    Next
    INDEX
    Explanations

    National Action, Public Credit, Early Origins

    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
     mega
    -0.79
    民間
    -0.72
    ļi
    -0.72
    Astronomy
    -0.71
     сегодня
    -0.69
     продъл
    -0.69
    個別
    -0.69
    mega
    -0.69
     Finalmente
    -0.68
     initializer
    -0.68
    POSITIVE LOGITS
     desperdic
    0.86
     dok
    0.86
     etme
    0.85
     systém
    0.82
     Giacomo
    0.81
     konsep
    0.79
    ∽
    0.77
    хами
    0.76
     cuja
    0.76
    Kash
    0.76
    Activations Density 0.001%

    No Known Activations