© 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. 10-GEMMASCOPE-RES-131K
    7. 86144
    Prev
    Next
    INDEX
    Explanations

    SA followed by characters/words

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

    The neuron is effectively inactive and does not respond to any text patterns.

    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
    
    -2.58
    
    -2.09
     hayal
    -2.09
     feiner
    -1.99
    鹮
    -1.98
    潆
    -1.93
    
    -1.88
     naudoti
    -1.85
    摇了
    -1.83
     ถ้า
    -1.78
    POSITIVE LOGITS
    In
    2.34
    is
    2.33
    (
    2.13
    0
    2.09
    да
    1.98
    As
    1.90
    s
    1.90
    ?
    1.83
     Ã
    1.80
    “
    1.77
    Activations Density 0.010%

    No Known Activations