© 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. 73834
    Prev
    Next
    INDEX
    Explanations

    urls and code snippets

    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
     ekos
    -1.29
     protesta
    -1.24
     sonda
    -1.23
     plafon
    -1.20
     konfigura
    -1.19
     lanterna
    -1.19
     biel
    -1.16
     seksi
    -1.16
     konfer
    -1.15
    callBack
    -1.15
    POSITIVE LOGITS
     on
    1.12
     first
    1.12
     it
    1.10
    i
    1.09
    V
    1.05
    H
    1.05
     terenie
    1.02
     within
    1.01
     has
    1.00
     at
    0.99
    Activations Density 0.042%

    No Known Activations