© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108715
    Prev
    Next
    INDEX
    Explanations

    emerging new trends

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

    The neuron strongly activates on the adjective “emerging” (often capitalized) marking noun phrases (e.g., “Emerging Journalist,” “emerging research areas,” “emerging growth company”).

    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
    <bos>
    -1.09
    
    -1.06
    ícias
    -1.06
    癶
    -1.05
     envol
    -1.02
     ensuing
    -1.01
    ⩕
    -0.98
     пароль
    -0.95
     spion
    -0.95
    륨
    -0.95
    POSITIVE LOGITS
     victorious
    1.31
     new
    1.27
     from
    1.27
     trends
    1.21
     as
    1.19
     technologies
    1.16
     during
    1.10
    لينا
    1.10
     leaders
    1.05
     During
    1.04
    Activations Density 0.021%

    No Known Activations