© 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. 111137
    Prev
    Next
    INDEX
    Explanations

    China, commerce, agriculture

    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
     Bolsonaro
    -1.04
    constexpr
    -0.97
    ​​​​​​​
    -0.88
     coronavirus
    -0.88
    uguetes
    -0.87
    iplin
    -0.86
    torie
    -0.83
    penes
    -0.83
    nullptr
    -0.82
    fini
    -0.82
    POSITIVE LOGITS
     Torch
    0.90
     AOL
    0.85
     Grange
    0.85
     Cisco
    0.84
     VISTA
    0.82
     SHIT
    0.79
     ENC
    0.79
     (_.
    0.78
     chỉnh
    0.78
     felicidade
    0.77
    Activations Density 0.036%

    No Known Activations