© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40040
    Prev
    Next
    INDEX
    Explanations

    #import statements

    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_22/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
    uário
    -0.94
    マニア
    -0.90
     violación
    -0.84
    ҿ
    -0.82
     mapStateToProps
    -0.82
    ĭ
    -0.82
    ственные
    -0.81
    んぼ
    -0.78
     only
    -0.78
     Arquivado
    -0.77
    POSITIVE LOGITS
     other
    0.90
    ἦ
    0.88
     Stufen
    0.88
     vốn
    0.86
    是一種
    0.85
    allero
    0.84
     Vedic
    0.83
     prêtre
    0.82
    вочка
    0.81
    别的
    0.80
    Activations Density 0.019%

    No Known Activations