© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44582
    Prev
    Next
    INDEX
    Explanations

    joining together or with

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

    The neuron fires on instances of the verb “join” (in any inflection) immediately followed by “in,” i.e. the phrase “join in” that signals participation.

    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
     you
    -2.36
     deux
    -1.93
     efectivo
    -1.82
    𝑀
    -1.80
     undergo
    -1.80
     potent
    -1.79
     satisfactory
    -1.76
     excelentes
    -1.72
     городского
    -1.71
     utiliser
    -1.69
    POSITIVE LOGITS
    
    1.88
     brasili
    1.81
    📢
    1.71
    ၜ
    1.66
     netizen
    1.62
     loca
    1.60
     enthousi
    1.60
     ridu
    1.56
     brillant
    1.56
    颪
    1.54
    Activations Density 0.005%

    No Known Activations