© 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. 73721
    Prev
    Next
    INDEX
    Explanations

    energy flux, error throw, permeate, delegates down

    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
     Whiting
    -0.73
    дей
    -0.69
     Philly
    -0.68
    flexGrow
    -0.68
     มิ
    -0.68
    alis
    -0.67
    scarpe
    -0.67
    colades
    -0.66
    razione
    -0.65
    ocardi
    -0.65
    POSITIVE LOGITS
     trickle
    4.50
    trick
    4.03
     trick
    3.84
     Trick
    3.50
    Trick
    3.16
     percol
    2.23
     cascade
    1.98
     ripple
    1.95
     cascading
    1.93
     cascades
    1.73
    Activations Density 0.069%

    No Known Activations