© 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. 66182
    Prev
    Next
    INDEX
    Explanations

    types of groups or parties

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

    The neuron is keyed to common coordinating connectors (especially “and,” “or,” “for,” hyphens, commas, etc.) that join or list items in a sentence.

    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
     Tourist
    -0.99
    ingos
    -0.83
    客厅
    -0.82
     домой
    -0.81
     Hierro
    -0.79
     Menor
    -0.77
     chiếc
    -0.76
     gode
    -0.75
     latine
    -0.74
     frågan
    -0.74
    POSITIVE LOGITS
     families
    2.64
     couples
    2.28
     groups
    2.13
    Families
    2.06
     Families
    1.97
     family
    1.84
    groups
    1.73
    couples
    1.72
     Groups
    1.70
     group
    1.69
    Activations Density 0.026%

    No Known Activations