© 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. 9671
    Prev
    Next
    INDEX
    Explanations

    constructors or definitions

    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
     zobaczyć
    -1.31
     skvě
    -1.30
    𓄹
    -1.20
    ಛ
    -1.20
     scherm
    -1.20
     Başkanı
    -1.19
    zdo
    -1.18
     ilustracji
    -1.18
     gebre
    -1.15
    ಝ
    -1.15
    POSITIVE LOGITS
    !!!!!!!
    1.18
    1.12
     !!!!
    1.11
     από
    1.09
    ('
    1.06
     
    1.05
     guz
    1.04
    </em>
    1.03
     again
    1.01
    SaveChangesAsync
    1.01
    Activations Density 0.002%
    No Known Activations