© 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. 75570
    Prev
    Next
    INDEX
    Explanations

    acts as role or function

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

    The main thing this neuron does is detect the third‐person singular present‐tense verb “acts.”

    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
    姈
    -2.22
     gän
    -1.99
    蒟
    -1.93
    帔
    -1.93
    何故
    -1.87
     trabajó
    -1.79
    OUTUBE
    -1.77
    ſures
    -1.77
    ších
    -1.74
     Garantía
    -1.74
    POSITIVE LOGITS
     a
    3.13
     in
    2.23
    en
    2.09
    或
    2.06
     et
    1.98
    </h5>
    1.97
    ;
    1.87
    at
    1.85
    ?”
    1.84
    an
    1.80
    Activations Density 0.003%

    No Known Activations