© 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. 61490
    Prev
    Next
    INDEX
    Explanations

    claimed to / that

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

    The neuron activates on various forms of the verb “claim” (e.g., claim, claimed, claiming).

    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
    
    -2.17
    e
    -2.11
    🌲
    -1.98
    \}$
    -1.90
     He
    -1.88
    жду
    -1.86
     February
    -1.85
    ２
    -1.77
    راین
    -1.76
    🐶
    -1.76
    POSITIVE LOGITS
    他自己
    2.38
    茀
    2.14
    乆
    2.14
    未必
    2.13
    ーーー
    2.11
    是自己
    2.06
     größte
    2.05
    喽
    2.05
    鸸
    2.03
     discrepancies
    2.00
    Activations Density 0.007%

    No Known Activations