© 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. 10985
    Prev
    Next
    INDEX
    Explanations

    django models or koinex api

    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
     here
    -1.17
    だったが
    -1.09
    がありますが
    -1.07
     you
    -1.03
    しましたが
    -0.98
    があるので
    -0.95
     होगी
    -0.91
     to
    -0.90
     kvad
    -0.90
    などが
    -0.89
    POSITIVE LOGITS
     его
    0.99
     Эти
    0.96
    のでしょう
    0.94
    のではない
    0.93
    WebElementEntity
    0.91
     procede
    0.91
     Затем
    0.91
     stwier
    0.90
    ְר
    0.89
     הוא
    0.88
    Activations Density 0.003%

    No Known Activations