© 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. 2993
    Prev
    Next
    INDEX
    Explanations

    javascript ajax data success

    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
     Partai
    -0.90
     menn
    -0.78
     Nasi
    -0.77
    ਜ
    -0.75
     Nasıl
    -0.73
    IDK
    -0.73
     kvar
    -0.72
    idk
    -0.71
    ounding
    -0.70
    福島
    -0.70
    POSITIVE LOGITS
     success
    1.55
    success
    1.38
     dataType
    1.35
    dataType
    1.30
    complete
    1.18
    DataType
    1.09
     complete
    1.05
     éxito
    0.97
     DataType
    0.94
    error
    0.91
    Activations Density 0.067%

    No Known Activations