© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 64997
    Prev
    Next
    INDEX
    Explanations

    both in

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

    This neuron fires strongly on occurrences of the word “both,” especially in “both … and …” coordination phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    えっ
    -1.14
    うーん
    -1.11
    を行いました
    -1.09
    他会
    -1.03
     vivement
    -1.00
     
    -0.99
    Заключение
    -0.96
     highly
    -0.91
    で一番
    -0.90
    たしか
    -0.88
    POSITIVE LOGITS
     singoli
    1.12
     bezüglich
    1.08
     singola
    1.01
     selve
    1.00
    håll
    0.98
     individual
    0.98
    ഡ
    0.98
     отдель
    0.97
    useNewUrlParser
    0.96
     zwyk
    0.94
    Activations Density 0.036%

    No Known Activations