© 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. 59199
    Prev
    Next
    INDEX
    Explanations

    import declarations

    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
     виправи
    -0.99
     frågor
    -0.97
    两人的
    -0.95
     nagu
    -0.91
    経緯
    -0.90
    ığınız
    -0.88
     tertawa
    -0.88
     poszczegól
    -0.87
    igua
    -0.86
     tavo
    -0.86
    POSITIVE LOGITS
     rappresent
    0.96
     ബ
    0.91
    ICATION
    0.90
     likely
    0.89
    formik
    0.88
    EINVAL
    0.84
    PropTypes
    0.83
     mesmo
    0.83
     seguire
    0.82
    Addressing
    0.81
    Activations Density 0.019%

    No Known Activations