© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36006
    Prev
    Next
    INDEX
    Explanations

    both X and Y

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

    This neuron detects occurrences of the word “both” (and similar two‐way coordinators linking two items).

    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
     темати
    -0.85
    modore
    -0.81
     etc
    -0.80
    ání
    -0.79
    estos
    -0.79
    等待
    -0.77
    nalités
    -0.77
    zondere
    -0.76
    FIM
    -0.74
    
    -0.74
    POSITIVE LOGITS
    含ま
    0.91
    IFICACIONES
    0.88
     aspetti
    0.86
     στοι
    0.84
     протягом
    0.84
    ∅
    0.84
    iteter
    0.82
     aspects
    0.82
    才會
    0.80
     possibly
    0.78
    Activations Density 0.138%

    No Known Activations