© 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. 31569
    Prev
    Next
    INDEX
    Explanations

    legal documents and technical specifications

    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
     most
    -0.99
     people
    -0.94
     any
    -0.94
     altres
    -0.93
     other
    -0.90
    ประมาณ
    -0.90
     almost
    -0.87
     numerous
    -0.85
     many
    -0.84
    дів
    -0.84
    POSITIVE LOGITS
    влении
    0.92
     această
    0.92
    choly
    0.90
     accompagné
    0.89
     hôm
    0.89
    stä
    0.88
     botón
    0.88
     coö
    0.86
    秶
    0.85
    ियां
    0.85
    Activations Density 0.000%

    No Known Activations