© 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. 11222
    Prev
    Next
    INDEX
    Explanations

    programmatic syntax 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
     other
    -1.13
    ⧠
    -1.10
     to
    -1.07
    otros
    -0.96
     otras
    -0.95
    部分
    -0.94
     others
    -0.94
     cierra
    -0.93
     digelar
    -0.91
     Schwangerschaft
    -0.91
    POSITIVE LOGITS
     carlo
    1.09
     ""
    1.07
    他們
    0.99
    #+#
    0.96
     spline
    0.95
     ')'
    0.94
     regio
    0.94
    以上です
    0.94
    
    0.93
     mambo
    0.93
    Activations Density 0.011%

    No Known Activations