© 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. 47737
    Prev
    Next
    INDEX
    Explanations

    court justice names

    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
    搵
    -0.75
     polyp
    -0.73
    Jk
    -0.73
    ranti
    -0.73
     кола
    -0.72
     Edmond
    -0.71
    ydable
    -0.71
     Nm
    -0.71
    Trax
    -0.71
    kiksi
    -0.70
    POSITIVE LOGITS
    agnos
    0.90
     shouldn
    0.81
    رت
    0.80
    日で
    0.80
     Roc
    0.76
    萌
    0.72
     Complexity
    0.72
    ilov
    0.70
    Pack
    0.69
     خود
    0.69
    Activations Density 0.003%

    No Known Activations