© 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. 10-GEMMASCOPE-RES-131K
    7. 74483
    Prev
    Next
    INDEX
    Explanations

    programming code, technical descriptions, or questions

    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_10/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
    还有
    -1.87
    环境
    -1.60
     הוא
    -1.59
     merasakan
    -1.55
    ）
    -1.52
     or
    -1.50
    ")
    -1.45
     είναι
    -1.45
    所有的
    -1.44
    由
    -1.44
    POSITIVE LOGITS
     We
    1.70
     that
    1.69
     who
    1.63
    ꦒ
    1.60
     colar
    1.59
    鱨
    1.57
    摞
    1.53
     clinica
    1.52
    $.
    1.43
     sobri
    1.41
    Activations Density 0.002%

    No Known Activations