© 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. 90104
    Prev
    Next
    INDEX
    Explanations

    enterprise solutions and products

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

    This neuron selectively activates on the corporate‐announcement language used when a company introduces or expands offerings—words like “introduces,” “new,” “services,” “announced,” and “upgrading.”

    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
     technischen
    -1.00
     Apesar
    -0.94
     Algunos
    -0.86
     młod
    -0.85
    尔斯
    -0.85
    Apesar
    -0.83
     Muitos
    -0.82
     estrictamente
    -0.82
     telefónica
    -0.81
     основном
    -0.81
    POSITIVE LOGITS
     solutions
    2.47
     solution
    2.05
     soluzioni
    1.79
    solutions
    1.57
     portfolio
    1.50
     offerings
    1.49
     products
    1.48
    solution
    1.41
     soluciones
    1.31
    Solutions
    1.25
    Activations Density 0.071%

    No Known Activations