© 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. 22-GEMMASCOPE-RES-131K
    7. 13821
    Prev
    Next
    INDEX
    Explanations

    to support it

    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
     može
    -0.93
     Incluye
    -0.90
     many
    -0.89
     Agrega
    -0.87
    Czytaj
    -0.86
     certain
    -0.85
     mnoho
    -0.84
     niektó
    -0.84
    んですよ
    -0.83
     Tamaño
    -0.83
    POSITIVE LOGITS
     its
    1.70
    それを
    1.49
    はその
    1.38
    它的
    1.35
     его
    1.30
     their
    1.27
     ее
    1.18
     jego
    1.14
    その
    1.13
     их
    1.13
    Activations Density 0.157%

    No Known Activations