© 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. 107488
    Prev
    Next
    INDEX
    Explanations

    adding style or a perfect touch

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

    The neuron fires on promotional action phrases—imperative or persuasive marketing calls to action (e.g. “add,” “take a virtual tour,” “makes a great”).

    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
     poszczegól
    -0.81
     моей
    -0.78
     sogenannten
    -0.78
     кү
    -0.78
     importantes
    -0.77
     berühmten
    -0.77
    nowrap
    -0.76
    includegraphics
    -0.76
     terrifying
    -0.75
     migliori
    -0.75
    POSITIVE LOGITS
     statement
    1.28
     style
    1.20
     any
    1.14
     your
    1.13
     update
    1.11
    statements
    1.08
     Statements
    1.04
     Statement
    1.02
     addition
    1.00
     Adding
    0.99
    Activations Density 0.048%

    No Known Activations