© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105145
    Prev
    Next
    INDEX
    Explanations

    y'all

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

    The neuron detects informal exclamatory interjections that start with “y” (e.g., “y’know,” “yikes,” “yippee,” “ya”).

    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
     at
    -2.34
     as
    -2.05
     from
    -2.00
     during
    -1.99
     by
    -1.93
    }$.
    -1.91
     using
    -1.88
     TAMBÉM
    -1.78
     –
    -1.78
    そして
    -1.71
    POSITIVE LOGITS
    泚
    2.64
    
    2.28
    ᠂
    2.11
    桫
    2.08
    ⬈
    2.02
    ↓
    2.00
    
    2.00
    cisi
    1.94
     prochaines
    1.93
    matically
    1.92
    Activations Density 0.008%

    No Known Activations