© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72607
    Prev
    Next
    INDEX
    Explanations

    closing code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on individual string literals (identifiers or filenames) appearing inside parentheses or directive calls (e.g. get('author'), include('autocomplete.php'), route('login')) in code or template markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    y
    -2.38
    t
    -1.89
    的
    -1.84
    勠
    -1.83
    Donativos
    -1.75
     チラシ
    -1.70
    骓
    -1.70
    Cuisine
    -1.68
    Välkommen
    -1.67
    ter
    -1.66
    POSITIVE LOGITS
    </strong>
    2.56
     same
    1.87
    tshell
    1.85
    salms
    1.80
     -.
    1.78
    ürnberg
    1.75
    aratus
    1.70
    }();
    1.70
                
    1.69
     ainsi
    1.69
    Activations Density 0.015%

    No Known Activations