© 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. 101548
    Prev
    Next
    INDEX
    Explanations

    business site

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

    The neuron highlights the principal content-bearing nouns that name the main subject or topic of each passage.

    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
     because
    -1.73
     it
    -1.71
     that
    -1.69
     bottes
    -1.65
    e
    -1.57
     amour
    -1.45
    
    -1.39
     uncommon
    -1.36
     these
    -1.35
     ?
    -1.35
    POSITIVE LOGITS
     construida
    1.71
    へと
    1.60
     dicha
    1.55
     to
    1.52
     instalada
    1.51
    Merkmale
    1.50
    בת
    1.48
     diseñada
    1.48
     unabhängig
    1.47
    fanfic
    1.47
    Activations Density 0.374%

    No Known Activations