© 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. 30809
    Prev
    Next
    INDEX
    Explanations

    data privacy and protection

    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
     although
    -0.79
     Ul
    -0.73
     this
    -0.73
     three
    -0.72
     after
    -0.71
     make
    -0.70
     Sun
    -0.69
     trends
    -0.69
    although
    -0.68
    ibin
    -0.68
    POSITIVE LOGITS
     processing
    2.19
     processors
    1.93
    Processing
    1.92
     Processing
    1.90
     processor
    1.78
     Processor
    1.77
    processing
    1.72
    Processor
    1.68
     controller
    1.66
     PROCESSING
    1.66
    Activations Density 0.011%

    No Known Activations