© 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. 10-GEMMASCOPE-RES-131K
    4. 104189
    Prev
    Next
    INDEX
    Explanations

    and his family/others

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

    The neuron is specifically triggering on the conjunction “and.”

    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
     they
    -1.88
     why
    -1.70
     soñar
    -1.45
     obtend
    -1.44
    tım
    -1.41
     atraer
    -1.41
     Drž
    -1.41
     simplemente
    -1.39
     is
    -1.39
     quieren
    -1.34
    POSITIVE LOGITS
     vasi
    1.78
     alha
    1.70
     umbro
    1.62
     masaj
    1.59
     saks
    1.56
     cotta
    1.55
     megane
    1.53
     Tbsp
    1.52
     seksi
    1.52
     peugeot
    1.51
    Activations Density 0.054%

    No Known Activations