© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78040
    Prev
    Next
    INDEX
    Explanations

    the preceding names of publications, officials, or authorities

    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
     chapéu
    -1.06
    ніка
    -1.02
    鸲
    -0.98
     ícone
    -0.97
     både
    -0.96
     («
    -0.96
    」、
    -0.95
    ܜ
    -0.93
     prêmio
    -0.93
     tênis
    -0.93
    POSITIVE LOGITS
     report
    2.06
     statement
    1.72
     article
    1.62
     authors
    1.34
     according
    1.34
     spokesman
    1.31
     spokesperson
    1.24
     wrote
    1.20
     says
    1.17
    文件中
    1.14
    Activations Density 0.023%

    No Known Activations