© 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. 13190
    Prev
    Next
    INDEX
    Explanations

    joint actions and cooperation

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

    The main thing this neuron does is find words and phrases that denote cooperation or joint efforts (e.g. “joint,” “cooperative,” “collaborative”).

    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
     in
    -1.41
     In
    -1.20
    .
    -1.20
     himself
    -1.20
     has
    -1.17
     employee
    -1.15
     органов
    -1.15
            
    -1.15
     )
    -1.14
     suoi
    -1.14
    POSITIVE LOGITS
    czeń
    1.41
    以上です
    1.36
     condiv
    1.36
     fenti
    1.32
     shared
    1.31
     between
    1.30
    collective
    1.29
     with
    1.27
    夕方
    1.26
     collectif
    1.23
    Activations Density 0.132%

    No Known Activations