© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48951
    Prev
    Next
    INDEX
    Explanations

    dictionary keys with tuples

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

    The neuron responds to numeric literals (sequences of digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     sabun
    -0.98
     vah
    -0.94
    かります
    -0.93
    Informationen
    -0.92
     美丽
    -0.92
    OOTDTY
    -0.92
     bronz
    -0.91
    毛病
    -0.91
     tragé
    -0.91
    ȼ
    -0.90
    POSITIVE LOGITS
    0.98
     riguardo
    0.98
     …
    0.97
    â
    0.93
    "

    0.91
                    
    0.87
    PHONY
    0.85
    fillType
    0.85
           
    0.85
    ……
    0.85
    Activations Density 0.054%
    No Known Activations