© 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. 72690
    Prev
    Next
    INDEX
    Explanations

    lesser-known, new, or overlooked things

    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
     bucal
    -0.95
     общего
    -0.95
    AtIndex
    -0.93
     bruin
    -0.93
    DAFTAR
    -0.92
     colonie
    -0.88
     shippuden
    -0.87
    digheid
    -0.87
    repository
    -0.86
     analis
    -0.86
    POSITIVE LOGITS
     new
    1.55
     unexplored
    1.26
     hitherto
    1.24
     unfamiliar
    1.21
     novel
    1.20
     rarely
    1.19
     seldom
    1.16
     marginalized
    1.12
     yeni
    1.10
    таки
    1.08
    Activations Density 0.073%

    No Known Activations