© 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. 63006
    Prev
    Next
    INDEX
    Explanations

    Court of Customs and Patent Appeals

    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
    וּ
    -0.73
     değer
    -0.72
    fs
    -0.71
    征
    -0.64
    voort
    -0.62
     ciencias
    -0.62
    enges
    -0.61
    ereg
    -0.60
     intercepted
    -0.60
    Anonymous
    -0.60
    POSITIVE LOGITS
     duur
    0.74
    LOC
    0.71
    orz
    0.68
     Horne
    0.68
     骨
    0.68
     Weimar
    0.67
     lumineux
    0.65
     Spi
    0.65
    แค
    0.65
    tite
    0.64
    Activations Density 0.087%

    No Known Activations