© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108292
    Prev
    Next
    INDEX
    Explanations

    geological time periods

    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
     late
    -0.97
    late
    -0.86
    Late
    -0.84
     LATE
    -0.82
     Late
    -0.82
     mid
    -0.81
     глуби
    -0.79
    productions
    -0.77
    以為
    -0.77
    Expanded
    -0.77
    POSITIVE LOGITS
     period
    1.09
     Period
    0.99
     Era
    0.98
     Epoch
    0.96
     Periods
    0.96
    period
    0.93
     Subsystem
    0.89
    epoch
    0.84
     epochs
    0.84
     epoch
    0.82
    Activations Density 0.020%

    No Known Activations