© 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. 34-GEMMASCOPE-RES-131K
    4. 91172
    Prev
    Next
    INDEX
    Explanations

    family, sibling, species, cancer

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

    scientific, medical, and legal terms in technical or academic contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires most strongly on rare or specialized key nouns—especially technical terms, proper names, or other distinctive domain‐specific words.

    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
    entrums
    -0.99
     ogrom
    -0.99
     zatem
    -0.98
    лів
    -0.91
     aquellas
    -0.88
    darth
    -0.86
    quelles
    -0.85
    
    -0.85
    ěž
    -0.85
     nombreuses
    -0.85
    POSITIVE LOGITS
     interaction
    1.36
    การ
    1.32
     action
    1.27
     actions
    1.27
     activity
    1.25
     traversal
    1.21
     usage
    1.16
     workouts
    1.16
     observations
    1.16
     involvement
    1.14
    Activations Density 0.292%

    No Known Activations