© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27900
    Prev
    Next
    INDEX
    Explanations

    code documentation and data types

    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
     the
    -1.17
     Flasche
    -1.15
    braz
    -1.07
     “
    -0.99
    josh
    -0.93
    subsubsection
    -0.92
     those
    -0.92
    huff
    -0.92
    bais
    -0.91
     Tasche
    -0.91
    POSITIVE LOGITS
     whose
    1.15
    ストラリア
    1.09
    ต้องการ
    1.07
     cần
    1.05
     yaşında
    1.01
    馬上
    0.99
     desired
    0.98
    CHAFT
    0.98
    ที่มี
    0.96
    ATIVA
    0.94
    Activations Density 0.028%

    No Known Activations