© 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. 92120
    Prev
    Next
    INDEX
    Explanations

    variety names and official titles

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

    The neuron fires on the central domain-specific nouns or subject headings that identify a document’s primary topic (e.g. “variety,” “plant,” “cultivar,” “license,” “currency,” etc.).

    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
    国外
    -1.10
    ,“
    -1.05
    ))->
    -1.02
     like
    -1.02
    이나
    -0.99
    >
    
    -0.99
     before
    -0.96
     while
    -0.94
    讓
    -0.93
    цезда
    -0.92
    POSITIVE LOGITS
     together
    1.32
     وذلك
    1.20
    together
    1.20
     Together
    1.02
     TOGETHER
    1.02
     to
    0.94
     Namely
    0.90
    Vendredi
    0.90
    ၎
    0.88
    atoday
    0.87
    Activations Density 0.075%

    No Known Activations