© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70138
    Prev
    Next
    INDEX
    Explanations

    actions to get, build, or manipulate

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

    The neuron activates on individual Chinese characters that are stand‐alone action verbs.

    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
    
    -2.14
     "..\..\
    -2.13
     samot
    -2.08
    sssss
    -2.05
     és
    -2.05
    蒟
    -2.03
     of
    -2.02
    理石
    -2.02
    媄
    -1.98
     și
    -1.97
    POSITIVE LOGITS
     the
    2.58
    ,”
    2.33
     mehrere
    1.99
    素晴
    1.91
    ぶつ
    1.85
    --
    1.84
     verschillende
    1.84
    苦手な
    1.83
    жли
    1.83
    your
    1.78
    Activations Density 0.008%

    No Known Activations