© 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. 72792
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions or adverbs

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

    The neuron strongly activates on character or person names (proper nouns).

    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
     it
    -2.08
     any
    -1.92
     in
    -1.78
     that
    -1.75
     at
    -1.55
     for
    -1.51
     because
    -1.50
     an
    -1.48
     many
    -1.37
     their
    -1.35
    POSITIVE LOGITS
     разных
    1.54
     différents
    1.45
    
    1.44
     suoi
    1.41
    Helping
    1.32
    莛
    1.30
     différentes
    1.30
     nô
    1.30
    lorn
    1.29
    骉
    1.29
    Activations Density 0.054%

    No Known Activations