© 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. 22-GEMMASCOPE-RES-131K
    7. 72261
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structures

    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_22/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
    generally
    -1.09
     broader
    -1.04
     .......
    -0.99
    usually
    -0.98
     qi
    -0.96
     früher
    -0.93
    以外は
    -0.93
     breite
    -0.92
    外面的
    -0.90
    なくなって
    -0.88
    POSITIVE LOGITS
     noteworthy
    1.13
     through
    1.12
     sooooo
    1.07
    こちらは
    1.06
     unbelievable
    1.02
     nestled
    0.98
     invigor
    0.97
     rudimentary
    0.96
     burgeoning
    0.94
     artful
    0.94
    Activations Density 0.024%

    No Known Activations