© 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. 68394
    Prev
    Next
    INDEX
    Explanations

    angular component declarations

    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
     cojín
    -1.24
     ویتامین
    -1.20
     phénom
    -1.17
     задний
    -1.13
     debout
    -1.11
    kių
    -1.11
     referrerpolicy
    -1.08
     Pharmacol
    -1.07
     sacré
    -1.05
    endwhile
    -1.05
    POSITIVE LOGITS
     {|
    1.35
     bahkan
    1.23
    There
    1.22
    These
    1.12
     menggunakan
    1.11
    readFileSync
    1.10
     продукта
    1.10
    ensión
    1.09
    vertx
    1.09
     noodzake
    1.09
    Activations Density 0.005%

    No Known Activations