© 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. 59360
    Prev
    Next
    INDEX
    Explanations

    console output and logging

    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
    Print
    -1.27
     PRINT
    -1.23
     print
    -1.23
    prints
    -1.22
     prints
    -1.15
     Print
    -1.15
    printed
    -1.14
     printed
    -1.09
     Printed
    -1.07
    printing
    -1.06
    POSITIVE LOGITS
     said
    1.23
    的说道
    0.84
     prides
    0.76
     interspersed
    0.75
    BIOL
    0.75
     geblieben
    0.75
    NSLog
    0.74
     screwed
    0.74
     pleasing
    0.73
     overlapped
    0.73
    Activations Density 0.026%

    No Known Activations