© 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. 70668
    Prev
    Next
    INDEX
    Explanations

    structured text and code delimiters

    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
     afbeelding
    -0.99
    dillera
    -0.92
    事儿
    -0.90
     musuh
    -0.89
     pengurus
    -0.88
     hvit
    -0.88
    Тогда
    -0.87
     afbeeldingen
    -0.84
    нити
    -0.84
    âmica
    -0.83
    POSITIVE LOGITS
     dergleichen
    0.91
    槊
    0.91
     directement
    0.88
    宜しくお願い
    0.88
     ferrovia
    0.88
     Gattung
    0.85
    subsubsection
    0.84
    byl
    0.81
     nobre
    0.81
     récit
    0.79
    Activations Density 0.010%

    No Known Activations