© 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. 39268
    Prev
    Next
    INDEX
    Explanations

    code syntax and attributes

    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
     such
    -1.27
    nantes
    -1.25
     benefícios
    -1.23
    の方も
    -1.22
     you
    -1.14
    corrhi
    -1.13
    쾅
    -1.11
    cioni
    -1.10
     negócios
    -1.09
    我要
    -1.09
    POSITIVE LOGITS
     although
    1.02
    Orchid
    1.02
     inquisitive
    1.00
    と思いました
    0.99
    Instru
    0.99
     Although
    0.99
    一定的
    0.98
    Redes
    0.98
    と思ったら
    0.98
     sill
    0.97
    Activations Density 0.003%

    No Known Activations