© 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. 57647
    Prev
    Next
    INDEX
    Explanations

    attractant / One of Four

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

    The neuron fires on decimal‐formatted version numbers (floating numeric tokens like “2.17.1,” “0.7.0,” etc.).

    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
    骓
    -2.70
    >
    -2.48
    ’
    -2.28
    ſſel
    -2.27
    月下
    -2.11
     perna
    -2.09
    。『
    -2.09
    却没有
    -2.08
     добраться
    -2.00
     corda
    -1.99
    POSITIVE LOGITS
    </h4>
    2.69
    
    2.64
    </em>
    2.61
    に行った
    2.30
     ส์
    2.23
    粁
    2.22
    素晴らしい
    2.20
    咣
    2.20
     Всё
    2.13
    噼
    2.13
    Activations Density 0.002%

    No Known Activations