© 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. 34-GEMMASCOPE-RES-131K
    7. 73682
    Prev
    Next
    INDEX
    Explanations

    together/each other

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

    The neuron fires most strongly on the single longest contiguous token in each context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    师
    -0.81
     lambat
    -0.72
    وافق
    -0.72
     stolet
    -0.71
    Dono
    -0.69
     小学生
    -0.69
     focused
    -0.67
    راجع
    -0.66
    iert
    -0.66
     neatly
    -0.66
    POSITIVE LOGITS
    กัน
    3.45
     nhau
    2.78
     друг
    1.48
     elkaar
    1.38
     eachother
    1.28
     varandra
    1.21
     together
    1.19
    กับ
    1.09
     einander
    1.00
    together
    0.98
    Activations Density 0.029%

    No Known Activations