© 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. 10-GEMMASCOPE-RES-131K
    7. 65187
    Prev
    Next
    INDEX
    Explanations

    introduces exceptions or conditions

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

    The neuron activates on the word “except,” marking contrastive or exception clauses.

    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
    );
    -2.89
                        
    -2.17
    '];
    -1.95
    ๖
    -1.92
     tetapi
    -1.88
    ⼥
    -1.88
    骘
    -1.80
     and
    -1.80
     more
    -1.77
     semua
    -1.75
    POSITIVE LOGITS
    on
    2.78
    沵
    2.45
    ᾗ
    2.20
    だいたい
    2.14
     extravag
    2.09
     accented
    2.09
     the
    2.06
    什么的
    2.05
    的情绪
    2.05
    何故
    2.02
    Activations Density 0.024%

    No Known Activations