© 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. 91319
    Prev
    Next
    INDEX
    Explanations

    social media engagement

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

    The neuron detects numeric expressions and quantitative figures (e.g. counts, measurements, frequencies) in the text.

    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
     GOOGLE
    -1.14
    mouseX
    -0.98
     paypal
    -0.95
    attacker
    -0.93
     AMAZON
    -0.90
     Planta
    -0.88
    GOOGLE
    -0.87
     OpenStreetMap
    -0.86
     PayPal
    -0.86
    icot
    -0.85
    POSITIVE LOGITS
     engagement
    1.63
     algorithm
    1.46
     content
    1.45
     follower
    1.34
     organic
    1.31
     posts
    1.30
     Engagement
    1.29
     audience
    1.26
     followers
    1.23
    Engagement
    1.23
    Activations Density 0.017%

    No Known Activations