© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102603
    Prev
    Next
    INDEX
    Explanations

    Accenture, market, transformation

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

    This neuron doesn’t respond to any particular words or meanings but rather to how far you are into a stretch of running text, ramping up its activation as you move toward the end of a sentence or continuous clause.

    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
    śnia
    -0.96
    JButton
    -0.93
     neoliberal
    -0.91
     låter
    -0.90
     eccl
    -0.85
    mero
    -0.84
     maux
    -0.84
    élica
    -0.84
     através
    -0.82
    Anyways
    -0.82
    POSITIVE LOGITS
     adjacent
    1.11
     talent
    1.08
    ikka
    1.03
    deauna
    0.98
     disrupted
    0.98
     Capabilities
    0.97
     next
    0.95
     enabled
    0.94
    érons
    0.92
    łaszcza
    0.92
    Activations Density 0.026%

    No Known Activations