© 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. 34-GEMMASCOPE-RES-131K
    7. 97818
    Prev
    Next
    INDEX
    Explanations

    personal accounts and questions

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

    This neuron activates on numeric tokens, especially larger numbers.

    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
     foran
    -1.66
     conector
    -1.63
     💀
    -1.51
    😈
    -1.48
     ❓
    -1.47
     🌸
    -1.45
     🖤
    -1.44
     ❤️❤️
    -1.43
     mercedes
    -1.41
     !?
    -1.38
    POSITIVE LOGITS
    そのため
    1.85
    They
    1.74
    ↵↵↵
    1.70
     Empfindung
    1.69
     breiten
    1.67
     hugely
    1.67
     largely
    1.63
     Absicht
    1.62
     erwäh
    1.60
     wesentlichen
    1.60
    Activations Density 0.036%

    No Known Activations