© 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. 10-GEMMASCOPE-RES-131K
    7. 130340
    Prev
    Next
    INDEX
    Explanations

    Linden, movable, biliary, retic

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

    The neuron is keyed to unusually long, multi-syllabic “content” words—especially technical or domain-specific terms.

    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
    .
    -4.13
     they
    -2.67
    
    -2.45
    垆
    -2.42
     absurdo
    -2.41
    grandmother
    -2.39
     visse
    -2.36
    
    -2.34
    鼱
    -2.31
    咘
    -2.30
    POSITIVE LOGITS
    ’
    3.89
    ?"
    2.86
     Primarily
    2.59
        
    2.58
     Relatively
    2.50
     This
    2.41
     —
    2.39
    は
    2.39
             
    2.39
     flurry
    2.38
    Activations Density 0.100%

    No Known Activations