© 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. 34-GEMMASCOPE-RES-131K
    7. 76023
    Prev
    Next
    INDEX
    Explanations

    regular expression

    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_34/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
    
    -0.68
     function
    -0.68
    rees
    -0.67
    Matcher
    -0.67
     praktischen
    -0.66
     addressed
    -0.65
     höchsten
    -0.65
    しても
    -0.64
    倫
    -0.64
     zdjęcie
    -0.63
    POSITIVE LOGITS
     Reg
    1.09
     "^
    1.08
     '\\
    1.01
     Regular
    0.98
    Regular
    0.94
     regular
    0.92
     REG
    0.90
     "\\
    0.90
     capturing
    0.89
     regul
    0.89
    Activations Density 0.062%

    No Known Activations