© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66335
    Prev
    Next
    INDEX
    Explanations

    data field names, id, date, image

    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
     all
    -0.90
     userType
    -0.88
     Suomen
    -0.83
     its
    -0.80
     During
    -0.77
     userDetails
    -0.74
     roomId
    -0.74
     얻
    -0.72
    <?
    -0.72
     Wurzel
    -0.69
    POSITIVE LOGITS
    lename
    0.94
    UserId
    0.91
     img
    0.90
    să
    0.88
     date
    0.85
     image
    0.85
    charAt
    0.84
     Wav
    0.84
    IndexOutOfBounds
    0.84
     Vân
    0.84
    Activations Density 0.005%

    No Known Activations