© 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. 10-GEMMASCOPE-RES-131K
    7. 214
    Prev
    Next
    INDEX
    Explanations

    ) {

    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_10/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
    dzić
    -2.14
     a
    -2.00
     them
    -1.98
    了一個
    -1.79
    at
    -1.76
    N
    -1.73
     dolorosa
    -1.73
     ответить
    -1.72
    In
    -1.71
    年は
    -1.70
    POSITIVE LOGITS
     they
    2.28
    赑
    2.23
     ktore
    2.23
     inmediata
    2.17
     它
    2.09
     detener
    2.08
     envejec
    2.05
     тази
    2.05
     extremadamente
    2.03
     это
    1.98
    Activations Density 0.021%

    No Known Activations