© 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. 2538
    Prev
    Next
    INDEX
    Explanations

    to followed by an action

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

    The neuron fires on verbs of decision or intent—especially the phrase “decided to” (and its variants indicating someone deciding to do something).

    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
     decide
    -1.53
    ได้
    -1.52
     deciding
    -1.40
     Decide
    -1.38
     decidir
    -1.30
     understand
    -1.25
    szám
    -1.24
     decisions
    -1.20
     décide
    -1.16
    lámpara
    -1.15
    POSITIVE LOGITS
    不再
    1.01
     воспользоваться
    1.00
     go
    0.99
     take
    0.98
     use
    0.96
    还是
    0.95
    éos
    0.94
     or
    0.94
     noong
    0.94
    されていない
    0.94
    Activations Density 0.044%

    No Known Activations